Project import generated by Copybara.

GitOrigin-RevId: f4b1fe3f15810450fb6539e733f6a260d3ee082c

.bazelrc

@@ -5,9 +5,12 @@ common --experimental_repo_remote_exec
 
 # Basic build settings
 build --jobs 128
-build --define='absl=1'
+build --define='absl=1'  # for gtest
 build --enable_platform_specific_config
 
+# Enable stack traces
+test --test_env="GTEST_INSTALL_FAILURE_SIGNAL_HANDLER=1"
+
 # Linux
 build:linux --cxxopt=-std=c++17
 build:linux --host_cxxopt=-std=c++17

.bazelversion

@@ -0,0 +1 @@
+3.7.2

.github/ISSUE_TEMPLATE/00-build-installation-issue.md

@@ -0,0 +1,27 @@
+---
+name: "Build/Installation Issue"
+about: Use this template for build/installation issues
+labels: type:build/install
+
+---
+<em>Please make sure that this is a build/installation issue and also refer to the [troubleshooting](https://google.github.io/mediapipe/getting_started/troubleshooting.html) documentation before raising any issues.</em>
+
+**System information** (Please provide as much relevant information as possible)
+- OS Platform and Distribution (e.g. Linux Ubuntu 16.04, Android 11, iOS 14.4):
+- Compiler version (e.g. gcc/g++ 8 /Apple clang version 12.0.0):
+- Programming Language and version ( e.g. C++ 14, Python 3.6, Java ):
+- Installed using virtualenv? pip? Conda? (if python):
+- [MediaPipe version](https://github.com/google/mediapipe/releases):
+- Bazel version:
+- XCode and Tulsi versions (if iOS):
+- Android SDK and NDK versions (if android):
+- Android [AAR](https://google.github.io/mediapipe/getting_started/android_archive_library.html) ( if android):
+- OpenCV version (if running on desktop):
+
+**Describe the problem**:
+
+
+**[Provide the exact sequence of commands / steps that you executed before running into the problem](https://google.github.io/mediapipe/getting_started/getting_started.html):**
+
+**Complete Logs:**
+Include Complete Log information or source code that would be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached:

.github/ISSUE_TEMPLATE/10-solution-issue.md

@@ -0,0 +1,26 @@
+---
+name: "Solution Issue"
+about: Use this template for assistance with a specific mediapipe solution, such as "Pose" or "Iris", including inference model usage/training, solution-specific calculators, etc.
+labels: type:support
+
+---
+<em>Please make sure that this is a [solution](https://google.github.io/mediapipe/solutions/solutions.html) issue.<em>
+
+**System information** (Please provide as much relevant information as possible)
+- Have I written custom code (as opposed to using a stock example script provided in Mediapipe):
+- OS Platform and Distribution (e.g., Linux Ubuntu 16.04, Android 11, iOS 14.4):
+- [MediaPipe version](https://github.com/google/mediapipe/releases):
+- Bazel version:
+- Solution (e.g. FaceMesh, Pose, Holistic):
+- Programming Language and version ( e.g. C++, Python, Java):
+
+**Describe the expected behavior:**
+
+**Standalone code you may have used to try to get what you need :**
+
+If there is a problem, provide a reproducible test case that is the bare minimum necessary to generate the problem. If possible, please share a link to Colab/repo link /any notebook:
+
+**Other info / Complete Logs :**
+Include any logs or source code that would be helpful to
+diagnose the problem. If including tracebacks, please include the full
+traceback. Large logs and files should be attached:

.github/ISSUE_TEMPLATE/20-documentation-issue.md

@@ -0,0 +1,51 @@
+---
+name: "Documentation Issue"
+about: Use this template for documentation related issues
+labels: type:docs
+
+---
+Thank you for submitting a MediaPipe documentation issue.
+The MediaPipe docs are open source! To get involved, read the documentation Contributor Guide
+## URL(s) with the issue:
+
+Please provide a link to the documentation entry, for example: https://github.com/google/mediapipe/blob/master/docs/solutions/face_mesh.md#models
+
+## Description of issue (what needs changing):
+
+Kinds of documentation problems:
+
+### Clear description
+
+For example, why should someone use this method? How is it useful?
+
+### Correct links
+
+Is the link to the source code correct?
+
+### Parameters defined
+Are all parameters defined and formatted correctly?
+
+### Returns defined
+
+Are return values defined?
+
+### Raises listed and defined
+
+Are the errors defined? For example,
+
+### Usage example
+
+Is there a usage example?
+
+See the API guide:
+on how to write testable usage examples.
+
+### Request visuals, if applicable
+
+Are there currently visuals? If not, will it clarify the content?
+
+### Submit a pull request?
+
+Are you planning to also submit a pull request to fix the issue? See the docs
+https://github.com/google/mediapipe/blob/master/CONTRIBUTING.md
+

.github/ISSUE_TEMPLATE/30-bug-issue.md

@@ -0,0 +1,32 @@
+---
+name: "Bug Issue"
+about: Use this template for reporting a bug
+labels: type:bug
+
+---
+<em>Please make sure that this is a bug and also refer to the [troubleshooting](https://google.github.io/mediapipe/getting_started/troubleshooting.html), FAQ documentation before raising any issues.</em>
+
+**System information** (Please provide as much relevant information as possible)
+
+- Have I written custom code (as opposed to using a stock example script provided in MediaPipe):
+- OS Platform and Distribution (e.g., Linux Ubuntu 16.04, Android 11, iOS 14.4):
+- Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device:
+- Browser and version (e.g. Google Chrome, Safari) if the issue happens on browser:
+- Programming Language and version ( e.g. C++, Python, Java):
+- [MediaPipe version](https://github.com/google/mediapipe/releases):
+- Bazel version (if compiling from source):
+- Solution ( e.g. FaceMesh, Pose, Holistic ):
+- Android Studio, NDK, SDK versions (if issue is related to building in Android environment):
+- Xcode & Tulsi version (if issue is related to building for iOS):
+
+**Describe the current behavior:**
+
+**Describe the expected behavior:**
+
+**Standalone code to reproduce the issue:**
+Provide a reproducible test case that is the bare minimum necessary to replicate the problem. If possible, please share a link to Colab/repo link /any notebook:
+
+**Other info / Complete Logs :**
+ Include any logs or source code that would be helpful to
+diagnose the problem. If including tracebacks, please include the full
+traceback. Large logs and files should be attached

.github/ISSUE_TEMPLATE/40-feature-request.md

@@ -0,0 +1,24 @@
+---
+name: "Feature Request"
+about: Use this template for raising a feature request
+labels: type:feature
+
+---
+<em>Please make sure that this is a feature request.</em>
+
+**System information** (Please provide as much relevant information as possible)
+
+- MediaPipe Solution (you are using):
+- Programming language : C++/typescript/Python/Objective C/Android Java
+- Are you willing to contribute it (Yes/No):
+
+
+**Describe the feature and the current behavior/state:**
+
+**Will this change the current api? How?**
+
+**Who will benefit with this feature?**
+
+**Please specify the use cases for this feature:**
+
+**Any Other info:**

.github/ISSUE_TEMPLATE/50-other-issues.md

@@ -0,0 +1,14 @@
+---
+name: "Other Issue"
+about: Use this template for any other non-support related issues.
+labels: type:others
+
+---
+This template is for miscellaneous issues not covered by the other issue categories
+
+For questions on how to work with MediaPipe, or support for problems that are not verified bugs in MediaPipe, please go to [StackOverflow](https://stackoverflow.com/questions/tagged/mediapipe) and [Slack](https://mediapipe.page.link/joinslack) communities.
+
+If you are reporting a vulnerability, please use the [dedicated reporting process](https://github.com/google/mediapipe/security).
+
+For high-level discussions about MediaPipe, please post to discuss@mediapipe.org, for questions about the development or internal workings of MediaPipe, or if you would like to know how to contribute to MediaPipe, please post to developers@mediapipe.org.
+

.github/bot_config.yml

@@ -0,0 +1,18 @@
+# Copyright 2021 The MediaPipe Authors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ============================================================================
+
+# A list of assignees
+assignees:
+   - sgowroji

.github/stale.yml

@@ -0,0 +1,34 @@
+# Copyright 2021 The MediaPipe Authors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ============================================================================
+#
+# This file was assembled from multiple pieces, whose use is documented
+# throughout. Please refer to the TensorFlow dockerfiles documentation
+# for more information.
+
+# Number of days of inactivity before an Issue or Pull Request becomes stale
+daysUntilStale: 7
+# Number of days of inactivity before a stale Issue or Pull Request is closed
+daysUntilClose: 7
+# Only issues or pull requests with all of these labels are checked if stale. Defaults to `[]` (disabled)
+onlyLabels:
+ - stat:awaiting response
+# Comment to post when marking as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs. Thank you.
+# Comment to post when removing the stale label. Set to `false` to disable
+unmarkComment: false
+closeComment: >
+  Closing as stale. Please reopen if you'd like to work on this further.

Dockerfile

@@ -23,6 +23,7 @@ ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
         build-essential \
+        gcc-8 g++-8 \
         ca-certificates \
         curl \
         ffmpeg \
@@ -44,6 +45,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
+RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-8 100 --slave /usr/bin/g++ g++ /usr/bin/g++-8
 RUN pip3 install --upgrade setuptools
 RUN pip3 install wheel
 RUN pip3 install future
@@ -54,7 +56,7 @@ RUN pip3 install tf_slim
 RUN ln -s /usr/bin/python3 /usr/bin/python
 
 # Install bazel
-ARG BAZEL_VERSION=3.4.1
+ARG BAZEL_VERSION=3.7.2
 RUN mkdir /bazel && \
     wget --no-check-certificate -O /bazel/installer.sh "https://github.com/bazelbuild/bazel/releases/download/${BAZEL_VERSION}/b\
 azel-${BAZEL_VERSION}-installer-linux-x86_64.sh" && \

MANIFEST.in

@@ -8,3 +8,13 @@ include README.md
 include requirements.txt
 
 recursive-include mediapipe/modules *.tflite *.txt *.binarypb
+exclude mediapipe/modules/face_detection/face_detection_full_range.tflite
+exclude mediapipe/modules/objectron/object_detection_3d_chair_1stage.tflite
+exclude mediapipe/modules/objectron/object_detection_3d_sneakers_1stage.tflite
+exclude mediapipe/modules/objectron/object_detection_3d_sneakers.tflite
+exclude mediapipe/modules/objectron/object_detection_3d_chair.tflite
+exclude mediapipe/modules/objectron/object_detection_3d_camera.tflite
+exclude mediapipe/modules/objectron/object_detection_3d_cup.tflite
+exclude mediapipe/modules/objectron/object_detection_ssd_mobilenetv2_oidv4_fp16.tflite
+exclude mediapipe/modules/pose_landmark/pose_landmark_lite.tflite
+exclude mediapipe/modules/pose_landmark/pose_landmark_heavy.tflite

README.md

@@ -34,17 +34,18 @@ Hair Segmentation
 
 []()                                                                                      | [Android](https://google.github.io/mediapipe/getting_started/android) | [iOS](https://google.github.io/mediapipe/getting_started/ios) | [C++](https://google.github.io/mediapipe/getting_started/cpp) | [Python](https://google.github.io/mediapipe/getting_started/python) | [JS](https://google.github.io/mediapipe/getting_started/javascript) | [Coral](https://github.com/google/mediapipe/tree/master/mediapipe/examples/coral/README.md)
 :---------------------------------------------------------------------------------------- | :-------------------------------------------------------------: | :-----------------------------------------------------: | :-----------------------------------------------------: | :-----------------------------------------------------------: | :-----------------------------------------------------------: | :--------------------------------------------------------------------:
-[Face Detection](https://google.github.io/mediapipe/solutions/face_detection)                   | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               | ✅
+[Face Detection](https://google.github.io/mediapipe/solutions/face_detection)                   | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             | ✅
 [Face Mesh](https://google.github.io/mediapipe/solutions/face_mesh)                             | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Iris](https://google.github.io/mediapipe/solutions/iris)                                       | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               |
 [Hands](https://google.github.io/mediapipe/solutions/hands)                                     | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Pose](https://google.github.io/mediapipe/solutions/pose)                                       | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Holistic](https://google.github.io/mediapipe/solutions/holistic)                               | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
+[Selfie Segmentation](https://google.github.io/mediapipe/solutions/selfie_segmentation)         | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Hair Segmentation](https://google.github.io/mediapipe/solutions/hair_segmentation)             | ✅                                                               |                                                         | ✅                                                       |                                                               |                                                               |
 [Object Detection](https://google.github.io/mediapipe/solutions/object_detection)               | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               | ✅
 [Box Tracking](https://google.github.io/mediapipe/solutions/box_tracking)                       | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               |
 [Instant Motion Tracking](https://google.github.io/mediapipe/solutions/instant_motion_tracking) | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
-[Objectron](https://google.github.io/mediapipe/solutions/objectron)                             | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
+[Objectron](https://google.github.io/mediapipe/solutions/objectron)                             | ✅                                                               |                                                         | ✅                                                       | ✅                                                             | ✅                                                             |
 [KNIFT](https://google.github.io/mediapipe/solutions/knift)                                     | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
 [AutoFlip](https://google.github.io/mediapipe/solutions/autoflip)                               |                                                                 |                                                         | ✅                                                       |                                                               |                                                               |
 [MediaSequence](https://google.github.io/mediapipe/solutions/media_sequence)                    |                                                                 |                                                         | ✅                                                       |                                                               |                                                               |
@@ -54,46 +55,22 @@ See also
 [MediaPipe Models and Model Cards](https://google.github.io/mediapipe/solutions/models)
 for ML models released in MediaPipe.
 
-## MediaPipe in Python
-
-MediaPipe offers customizable Python solutions as a prebuilt Python package on
-[PyPI](https://pypi.org/project/mediapipe/), which can be installed simply with
-`pip install mediapipe`. It also provides tools for users to build their own
-solutions. Please see
-[MediaPipe in Python](https://google.github.io/mediapipe/getting_started/python)
-for more info.
-
-## MediaPipe on the Web
-
-MediaPipe on the Web is an effort to run the same ML solutions built for mobile
-and desktop also in web browsers. The official API is under construction, but
-the core technology has been proven effective. Please see
-[MediaPipe on the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html)
-in Google Developers Blog for details.
-
-You can use the following links to load a demo in the MediaPipe Visualizer, and
-over there click the "Runner" icon in the top bar like shown below. The demos
-use your webcam video as input, which is processed all locally in real-time and
-never leaves your device.
-
-![visualizer_runner](docs/images/visualizer_runner.png)
-
-*   [MediaPipe Face Detection](https://viz.mediapipe.dev/demo/face_detection)
-*   [MediaPipe Iris](https://viz.mediapipe.dev/demo/iris_tracking)
-*   [MediaPipe Iris: Depth-from-Iris](https://viz.mediapipe.dev/demo/iris_depth)
-*   [MediaPipe Hands](https://viz.mediapipe.dev/demo/hand_tracking)
-*   [MediaPipe Hands (palm/hand detection only)](https://viz.mediapipe.dev/demo/hand_detection)
-*   [MediaPipe Pose](https://viz.mediapipe.dev/demo/pose_tracking)
-*   [MediaPipe Hair Segmentation](https://viz.mediapipe.dev/demo/hair_segmentation)
-
 ## Getting started
 
-Learn how to [install](https://google.github.io/mediapipe/getting_started/install)
-MediaPipe and
-[build example applications](https://google.github.io/mediapipe/getting_started/building_examples),
-and start exploring our ready-to-use
-[solutions](https://google.github.io/mediapipe/solutions/solutions) that you can
-further extend and customize.
+To start using MediaPipe
+[solutions](https://google.github.io/mediapipe/solutions/solutions) with only a few
+lines code, see example code and demos in
+[MediaPipe in Python](https://google.github.io/mediapipe/getting_started/python) and
+[MediaPipe in JavaScript](https://google.github.io/mediapipe/getting_started/javascript).
+
+To use MediaPipe in C++, Android and iOS, which allow further customization of
+the [solutions](https://google.github.io/mediapipe/solutions/solutions) as well as
+building your own, learn how to
+[install](https://google.github.io/mediapipe/getting_started/install) MediaPipe and
+start building example applications in
+[C++](https://google.github.io/mediapipe/getting_started/cpp),
+[Android](https://google.github.io/mediapipe/getting_started/android) and
+[iOS](https://google.github.io/mediapipe/getting_started/ios).
 
 The source code is hosted in the
 [MediaPipe Github repository](https://github.com/google/mediapipe), and you can
@@ -102,6 +79,15 @@ run code search using
 
 ## Publications
 
+*   [Bringing artworks to life with AR](https://developers.googleblog.com/2021/07/bringing-artworks-to-life-with-ar.html)
+    in Google Developers Blog
+*   [Prosthesis control via Mirru App using MediaPipe hand tracking](https://developers.googleblog.com/2021/05/control-your-mirru-prosthesis-with-mediapipe-hand-tracking.html)
+    in Google Developers Blog
+*   [SignAll SDK: Sign language interface using MediaPipe is now available for
+    developers](https://developers.googleblog.com/2021/04/signall-sdk-sign-language-interface-using-mediapipe-now-available.html)
+    in Google Developers Blog
+*   [MediaPipe Holistic - Simultaneous Face, Hand and Pose Prediction, on Device](https://ai.googleblog.com/2020/12/mediapipe-holistic-simultaneous-face.html)
+    in Google AI Blog
 *   [Background Features in Google Meet, Powered by Web ML](https://ai.googleblog.com/2020/10/background-features-in-google-meet.html)
     in Google AI Blog
 *   [MediaPipe 3D Face Transform](https://developers.googleblog.com/2020/09/mediapipe-3d-face-transform.html)

WORKSPACE

@@ -2,16 +2,19 @@ workspace(name = "mediapipe")
 
 load("@bazel_tools//tools/build_defs/repo:http.bzl", "http_archive")
 
-skylib_version = "0.9.0"
 http_archive(
     name = "bazel_skylib",
     type = "tar.gz",
-    url = "https://github.com/bazelbuild/bazel-skylib/releases/download/{}/bazel_skylib-{}.tar.gz".format (skylib_version, skylib_version),
-    sha256 = "1dde365491125a3db70731e25658dfdd3bc5dbdfd11b840b3e987ecf043c7ca0",
+    urls = [
+        "https://github.com/bazelbuild/bazel-skylib/releases/download/1.0.3/bazel-skylib-1.0.3.tar.gz",
+        "https://mirror.bazel.build/github.com/bazelbuild/bazel-skylib/releases/download/1.0.3/bazel-skylib-1.0.3.tar.gz",
+    ],
+    sha256 = "1c531376ac7e5a180e0237938a2536de0c54d93f5c278634818e0efc952dd56c",
 )
+load("@bazel_skylib//:workspace.bzl", "bazel_skylib_workspace")
+bazel_skylib_workspace()
 load("@bazel_skylib//lib:versions.bzl", "versions")
-versions.check(minimum_bazel_version = "3.4.0")
-
+versions.check(minimum_bazel_version = "3.7.2")
 
 # ABSL cpp library lts_2020_09_23
 http_archive(
@@ -32,14 +35,14 @@ http_archive(
 
 http_archive(
     name = "rules_cc",
-    strip_prefix = "rules_cc-master",
-    urls = ["https://github.com/bazelbuild/rules_cc/archive/master.zip"],
+    strip_prefix = "rules_cc-main",
+    urls = ["https://github.com/bazelbuild/rules_cc/archive/main.zip"],
 )
 
 http_archive(
    name = "rules_foreign_cc",
-   strip_prefix = "rules_foreign_cc-master",
-   url = "https://github.com/bazelbuild/rules_foreign_cc/archive/master.zip",
+   strip_prefix = "rules_foreign_cc-0.1.0",
+   url = "https://github.com/bazelbuild/rules_foreign_cc/archive/0.1.0.zip",
 )
 
 load("@rules_foreign_cc//:workspace_definitions.bzl", "rules_foreign_cc_dependencies")
@@ -50,26 +53,19 @@ rules_foreign_cc_dependencies()
 all_content = """filegroup(name = "all", srcs = glob(["**"]), visibility = ["//visibility:public"])"""
 
 # GoogleTest/GoogleMock framework. Used by most unit-tests.
-# Last updated 2020-06-30.
+# Last updated 2021-07-02.
 http_archive(
     name = "com_google_googletest",
-    urls = ["https://github.com/google/googletest/archive/aee0f9d9b5b87796ee8a0ab26b7587ec30e8858e.zip"],
-    patches = [
-        # fix for https://github.com/google/googletest/issues/2817
-        "@//third_party:com_google_googletest_9d580ea80592189e6d44fa35bcf9cdea8bf620d6.diff"
-    ],
-    patch_args = [
-        "-p1",
-    ],
-    strip_prefix = "googletest-aee0f9d9b5b87796ee8a0ab26b7587ec30e8858e",
-    sha256 = "04a1751f94244307cebe695a69cc945f9387a80b0ef1af21394a490697c5c895",
+    urls = ["https://github.com/google/googletest/archive/4ec4cd23f486bf70efcc5d2caa40f24368f752e3.zip"],
+    strip_prefix = "googletest-4ec4cd23f486bf70efcc5d2caa40f24368f752e3",
+    sha256 = "de682ea824bfffba05b4e33b67431c247397d6175962534305136aa06f92e049",
 )
 
 # Google Benchmark library.
 http_archive(
     name = "com_google_benchmark",
-    urls = ["https://github.com/google/benchmark/archive/master.zip"],
-    strip_prefix = "benchmark-master",
+    urls = ["https://github.com/google/benchmark/archive/main.zip"],
+    strip_prefix = "benchmark-main",
     build_file = "@//third_party:benchmark.BUILD",
 )
 
@@ -117,7 +113,8 @@ http_archive(
 # libyuv
 http_archive(
     name = "libyuv",
-    urls = ["https://chromium.googlesource.com/libyuv/libyuv/+archive/refs/heads/master.tar.gz"],
+    # Error: operand type mismatch for `vbroadcastss' caused by commit 8a13626e42f7fdcf3a6acbb0316760ee54cda7d8.
+    urls = ["https://chromium.googlesource.com/libyuv/libyuv/+archive/2525698acba9bf9b701ba6b4d9584291a1f62257.tar.gz"],
     build_file = "@//third_party:libyuv.BUILD",
 )
 
@@ -160,11 +157,11 @@ http_archive(
 http_archive(
     name = "pybind11",
     urls = [
-        "https://storage.googleapis.com/mirror.tensorflow.org/github.com/pybind/pybind11/archive/v2.4.3.tar.gz",
-        "https://github.com/pybind/pybind11/archive/v2.4.3.tar.gz",
+        "https://storage.googleapis.com/mirror.tensorflow.org/github.com/pybind/pybind11/archive/v2.7.1.tar.gz",
+        "https://github.com/pybind/pybind11/archive/v2.7.1.tar.gz",
     ],
-    sha256 = "1eed57bc6863190e35637290f97a20c81cfe4d9090ac0a24f3bbf08f265eb71d",
-    strip_prefix = "pybind11-2.4.3",
+    sha256 = "616d1c42e4cf14fa27b2a4ff759d7d7b33006fdc5ad8fd603bb2c22622f27020",
+    strip_prefix = "pybind11-2.7.1",
     build_file = "@pybind11_bazel//:pybind11.BUILD",
 )
 
@@ -238,6 +235,20 @@ http_archive(
     url = "https://github.com/opencv/opencv/releases/download/3.2.0/opencv-3.2.0-ios-framework.zip",
 )
 
+http_archive(
+    name = "stblib",
+    strip_prefix = "stb-b42009b3b9d4ca35bc703f5310eedc74f584be58",
+    sha256 = "13a99ad430e930907f5611325ec384168a958bf7610e63e60e2fd8e7b7379610",
+    urls = ["https://github.com/nothings/stb/archive/b42009b3b9d4ca35bc703f5310eedc74f584be58.tar.gz"],
+    build_file = "@//third_party:stblib.BUILD",
+    patches = [
+        "@//third_party:stb_image_impl.diff"
+    ],
+    patch_args = [
+        "-p1",
+    ],
+)
+
 # You may run setup_android.sh to install Android SDK and NDK.
 android_ndk_repository(
     name = "androidndk",
@@ -304,8 +315,8 @@ http_archive(
 
 # Maven dependencies.
 
-RULES_JVM_EXTERNAL_TAG = "3.2"
-RULES_JVM_EXTERNAL_SHA = "82262ff4223c5fda6fb7ff8bd63db8131b51b413d26eb49e3131037e79e324af"
+RULES_JVM_EXTERNAL_TAG = "4.0"
+RULES_JVM_EXTERNAL_SHA = "31701ad93dbfe544d597dbe62c9a1fdd76d81d8a9150c2bf1ecf928ecdf97169"
 
 http_archive(
     name = "rules_jvm_external",
@@ -318,10 +329,11 @@ load("@rules_jvm_external//:defs.bzl", "maven_install")
 
 # Important: there can only be one maven_install rule. Add new maven deps here.
 maven_install(
-    name = "maven",
     artifacts = [
         "androidx.concurrent:concurrent-futures:1.0.0-alpha03",
-        "androidx.lifecycle:lifecycle-common:2.2.0",
+        "androidx.lifecycle:lifecycle-common:2.3.1",
+        "androidx.activity:activity:1.2.2",
+        "androidx.fragment:fragment:1.3.4",
         "androidx.annotation:annotation:aar:1.1.0",
         "androidx.appcompat:appcompat:aar:1.1.0-rc01",
         "androidx.camera:camera-core:1.0.0-beta10",
@@ -334,19 +346,21 @@ maven_install(
         "androidx.test.espresso:espresso-core:3.1.1",
         "com.github.bumptech.glide:glide:4.11.0",
         "com.google.android.material:material:aar:1.0.0-rc01",
-        "com.google.code.findbugs:jsr305:3.0.2",
-        "com.google.flogger:flogger-system-backend:0.3.1",
-        "com.google.flogger:flogger:0.3.1",
+        "com.google.auto.value:auto-value:1.8.1",
+        "com.google.auto.value:auto-value-annotations:1.8.1",
+        "com.google.code.findbugs:jsr305:latest.release",
+        "com.google.flogger:flogger-system-backend:latest.release",
+        "com.google.flogger:flogger:latest.release",
         "com.google.guava:guava:27.0.1-android",
         "com.google.guava:listenablefuture:1.0",
         "junit:junit:4.12",
         "org.hamcrest:hamcrest-library:1.3",
     ],
     repositories = [
-        "https://jcenter.bintray.com",
         "https://maven.google.com",
         "https://dl.google.com/dl/android/maven2",
         "https://repo1.maven.org/maven2",
+        "https://jcenter.bintray.com",
     ],
     fetch_sources = True,
     version_conflict_policy = "pinned",
@@ -363,10 +377,10 @@ http_archive(
     ],
 )
 
-#Tensorflow repo should always go after the other external dependencies.
-# 2020-12-07
-_TENSORFLOW_GIT_COMMIT = "f556709f4df005ad57fd24d5eaa0d9380128d3ba"
-_TENSORFLOW_SHA256= "9e157d4723921b48a974f645f70d07c8fd3c363569a0ac6ee85fec114d6459ea"
+# Tensorflow repo should always go after the other external dependencies.
+# 2021-07-29
+_TENSORFLOW_GIT_COMMIT = "52a2905cbc21034766c08041933053178c5d10e3"
+_TENSORFLOW_SHA256 = "06d4691bcdb700f3275fa0971a1585221c2b9f3dffe867963be565a6643d7f56"
 http_archive(
     name = "org_tensorflow",
     urls = [
@@ -383,5 +397,22 @@ http_archive(
     sha256 = _TENSORFLOW_SHA256,
 )
 
-load("@org_tensorflow//tensorflow:workspace.bzl", "tf_workspace")
-tf_workspace(tf_repo_name = "org_tensorflow")
+load("@org_tensorflow//tensorflow:workspace3.bzl", "tf_workspace3")
+tf_workspace3()
+load("@org_tensorflow//tensorflow:workspace2.bzl", "tf_workspace2")
+tf_workspace2()
+
+# Edge TPU
+http_archive(
+  name = "libedgetpu",
+  sha256 = "14d5527a943a25bc648c28a9961f954f70ba4d79c0a9ca5ae226e1831d72fe80",
+  strip_prefix = "libedgetpu-3164995622300286ef2bb14d7fdc2792dae045b7",
+  urls = [
+    "https://github.com/google-coral/libedgetpu/archive/3164995622300286ef2bb14d7fdc2792dae045b7.tar.gz"
+  ],
+)
+load("@libedgetpu//:workspace.bzl", "libedgetpu_dependencies")
+libedgetpu_dependencies()
+
+load("@coral_crosstool//:configure.bzl", "cc_crosstool")
+cc_crosstool(name = "crosstool")

build_desktop_examples.sh

@@ -17,15 +17,15 @@
 # Script to build/run all MediaPipe desktop example apps (with webcam input).
 #
 # To build and run all apps and store them in out_dir:
-#   $ ./build_ios_examples.sh -d out_dir
+#   $ ./build_desktop_examples.sh -d out_dir
 #   Omitting -d and the associated directory saves all generated apps in the
 #   current directory.
 # To build all apps and store them in out_dir:
-#   $ ./build_ios_examples.sh -d out_dir -b
+#   $ ./build_desktop_examples.sh -d out_dir -b
 #   Omitting -d and the associated directory saves all generated apps in the
 #   current directory.
 # To run all apps already stored in out_dir:
-#   $ ./build_ios_examples.sh -d out_dir -r
+#   $ ./build_desktop_examples.sh -d out_dir -r
 #   Omitting -d and the associated directory assumes all apps are in the current
 #   directory.
 
@@ -94,8 +94,10 @@ for app in ${apps}; do
       else
         graph_name="${target_name}/${target_name}"
       fi
-      if [[ ${target_name} == "iris_tracking" ||
+      if [[ ${target_name} == "holistic_tracking" ||
+            ${target_name} == "iris_tracking" ||
             ${target_name} == "pose_tracking" ||
+            ${target_name} == "selfie_segmentation" ||
             ${target_name} == "upper_body_pose_tracking" ]]; then
         graph_suffix="cpu"
       else

docs/framework_concepts/calculators.md

@@ -67,26 +67,26 @@ class CalculatorBase {
 
   // The subclasses of CalculatorBase must implement GetContract.
   // ...
-  static ::MediaPipe::Status GetContract(CalculatorContract* cc);
+  static absl::Status GetContract(CalculatorContract* cc);
 
   // Open is called before any Process() calls, on a freshly constructed
   // calculator.  Subclasses may override this method to perform necessary
   // setup, and possibly output Packets and/or set output streams' headers.
   // ...
-  virtual ::MediaPipe::Status Open(CalculatorContext* cc) {
-    return ::MediaPipe::OkStatus();
+  virtual absl::Status Open(CalculatorContext* cc) {
+    return absl::OkStatus();
   }
 
   // Processes the incoming inputs. May call the methods on cc to access
   // inputs and produce outputs.
   // ...
-  virtual ::MediaPipe::Status Process(CalculatorContext* cc) = 0;
+  virtual absl::Status Process(CalculatorContext* cc) = 0;
 
   // Is called if Open() was called and succeeded.  Is called either
   // immediately after processing is complete or after a graph run has ended
   // (if an error occurred in the graph).  ...
-  virtual ::MediaPipe::Status Close(CalculatorContext* cc) {
-    return ::MediaPipe::OkStatus();
+  virtual absl::Status Close(CalculatorContext* cc) {
+    return absl::OkStatus();
   }
 
   ...
@@ -187,7 +187,7 @@ node {
 ```
 
 In the calculator implementation, inputs and outputs are also identified by tag
-name and index number. In the function below input are output are identified:
+name and index number. In the function below input and output are identified:
 
 *   By index number: The combined input stream is identified simply by index
     `0`.
@@ -199,7 +199,7 @@ name and index number. In the function below input are output are identified:
 // c++ Code snippet describing the SomeAudioVideoCalculator GetContract() method
 class SomeAudioVideoCalculator : public CalculatorBase {
  public:
-  static ::mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).SetAny();
     // SetAny() is used to specify that whatever the type of the
     // stream is, it's acceptable.  This does not mean that any
@@ -209,13 +209,13 @@ class SomeAudioVideoCalculator : public CalculatorBase {
     cc->Outputs().Tag("VIDEO").Set<ImageFrame>();
     cc->Outputs().Get("AUDIO", 0).Set<Matrix>();
     cc->Outputs().Get("AUDIO", 1).Set<Matrix>();
-    return ::mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 ```
 
 ## Processing
 
-`Process()` called on a non-source node must return `::mediapipe::OkStatus()` to
+`Process()` called on a non-source node must return `absl::OkStatus()` to
 indicate that all went well, or any other status code to signal an error
 
 If a non-source calculator returns `tool::StatusStop()`, then this signals the
@@ -224,12 +224,12 @@ input streams will be closed (and remaining Packets will propagate through the
 graph).
 
 A source node in a graph will continue to have `Process()` called on it as long
-as it returns `::mediapipe::OkStatus(`). To indicate that there is no more data
-to be generated return `tool::StatusStop()`. Any other status indicates an error
-has occurred.
+as it returns `absl::OkStatus(`). To indicate that there is no more data to be
+generated return `tool::StatusStop()`. Any other status indicates an error has
+occurred.
 
-`Close()` returns `::mediapipe::OkStatus()` to indicate success. Any other
-status indicates a failure.
+`Close()` returns `absl::OkStatus()` to indicate success. Any other status
+indicates a failure.
 
 Here is the basic `Process()` function. It uses the `Input()` method (which can
 be used only if the calculator has a single input) to request its input data. It
@@ -238,22 +238,80 @@ and does the calculations. When done it releases the pointer when adding it to
 the output stream.
 
 ```c++
-::util::Status MyCalculator::Process() {
+absl::Status MyCalculator::Process() {
   const Matrix& input = Input()->Get<Matrix>();
   std::unique_ptr<Matrix> output(new Matrix(input.rows(), input.cols()));
   // do your magic here....
   //    output->row(n) =  ...
   Output()->Add(output.release(), InputTimestamp());
-  return ::mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 ```
 
+## Calculator options
+
+Calculators accept processing parameters through (1) input stream packets (2)
+input side packets, and (3) calculator options. Calculator options, if
+specified, appear as literal values in the `node_options` field of the
+`CalculatorGraphConfiguration.Node` message.
+
+```
+  node {
+    calculator: "TfLiteInferenceCalculator"
+    input_stream: "TENSORS:main_model_input"
+    output_stream: "TENSORS:main_model_output"
+    node_options: {
+      [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+        model_path: "mediapipe/models/detection_model.tflite"
+      }
+    }
+  }
+```
+
+The `node_options` field accepts the proto3 syntax.  Alternatively, calculator
+options can be specified in the `options` field using proto2 syntax.
+
+```
+  node {
+    calculator: "TfLiteInferenceCalculator"
+    input_stream: "TENSORS:main_model_input"
+    output_stream: "TENSORS:main_model_output"
+    node_options: {
+      [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+        model_path: "mediapipe/models/detection_model.tflite"
+      }
+    }
+  }
+```
+
+Not all calculators accept calcuator options. In order to accept options, a
+calculator will normally define a new protobuf message type to represent its
+options, such as `PacketClonerCalculatorOptions`. The calculator will then
+read that protobuf message in its `CalculatorBase::Open` method, and possibly
+also in its `CalculatorBase::GetContract` function or its
+`CalculatorBase::Process` method. Normally, the new protobuf message type will
+be defined as a protobuf schema using a ".proto" file and a
+`mediapipe_proto_library()` build rule.
+
+```
+  mediapipe_proto_library(
+      name = "packet_cloner_calculator_proto",
+      srcs = ["packet_cloner_calculator.proto"],
+      visibility = ["//visibility:public"],
+      deps = [
+          "//mediapipe/framework:calculator_options_proto",
+          "//mediapipe/framework:calculator_proto",
+      ],
+  )
+```
+
+
 ## Example calculator
 
 This section discusses the implementation of `PacketClonerCalculator`, which
 does a relatively simple job, and is used in many calculator graphs.
-`PacketClonerCalculator` simply produces a copy of its most recent input
-packets on demand.
+`PacketClonerCalculator` simply produces a copy of its most recent input packets
+on demand.
 
 `PacketClonerCalculator` is useful when the timestamps of arriving data packets
 are not aligned perfectly. Suppose we have a room with a microphone, light
@@ -279,8 +337,8 @@ input streams:
     imageframe of video data representing video collected from camera in the
     room with timestamp.
 
-Below is the implementation of the `PacketClonerCalculator`.  You can see
-the `GetContract()`, `Open()`, and `Process()` methods as well as the instance
+Below is the implementation of the `PacketClonerCalculator`. You can see the
+`GetContract()`, `Open()`, and `Process()` methods as well as the instance
 variable `current_` which holds the most recent input packets.
 
 ```c++
@@ -312,7 +370,7 @@ namespace mediapipe {
 //
 class PacketClonerCalculator : public CalculatorBase {
  public:
-  static ::mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     const int tick_signal_index = cc->Inputs().NumEntries() - 1;
     // cc->Inputs().NumEntries() returns the number of input streams
     // for the PacketClonerCalculator
@@ -322,10 +380,10 @@ class PacketClonerCalculator : public CalculatorBase {
       cc->Outputs().Index(i).SetSameAs(&cc->Inputs().Index(i));
     }
     cc->Inputs().Index(tick_signal_index).SetAny();
-    return ::mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  ::mediapipe::Status Open(CalculatorContext* cc) final {
+  absl::Status Open(CalculatorContext* cc) final {
     tick_signal_index_ = cc->Inputs().NumEntries() - 1;
     current_.resize(tick_signal_index_);
     // Pass along the header for each stream if present.
@@ -336,10 +394,10 @@ class PacketClonerCalculator : public CalculatorBase {
         // the header for the input stream of index i
       }
     }
-    return ::mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  ::mediapipe::Status Process(CalculatorContext* cc) final {
+  absl::Status Process(CalculatorContext* cc) final {
     // Store input signals.
     for (int i = 0; i < tick_signal_index_; ++i) {
       if (!cc->Inputs().Index(i).Value().IsEmpty()) {
@@ -355,7 +413,6 @@ class PacketClonerCalculator : public CalculatorBase {
               current_[i].At(cc->InputTimestamp()));
           // Add a packet to output stream of index i a packet from inputstream i
           // with timestamp common to all present inputs
-          //
         } else {
           cc->Outputs().Index(i).SetNextTimestampBound(
               cc->InputTimestamp().NextAllowedInStream());
@@ -364,7 +421,7 @@ class PacketClonerCalculator : public CalculatorBase {
         }
       }
     }
-    return ::mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
  private:
@@ -382,7 +439,7 @@ defined your calculator class, register it with a macro invocation
 REGISTER_CALCULATOR(calculator_class_name).
 
 Below is a trivial MediaPipe graph that has 3 input streams, 1 node
-(PacketClonerCalculator) and 3 output streams.
+(PacketClonerCalculator) and 2 output streams.
 
 ```proto
 input_stream: "room_mic_signal"
@@ -402,6 +459,6 @@ node {
 The diagram below shows how the `PacketClonerCalculator` defines its output
 packets (bottom) based on its series of input packets (top).
 
-| ![Graph using PacketClonerCalculator](../images/packet_cloner_calculator.png) |
-| :---------------------------------------------------------------------------: |
-| *Each time it receives a packet on its TICK input stream, the PacketClonerCalculator outputs the most recent packet from each of its input streams. The sequence of output packets (bottom) is determined by the sequence of input packets (top) and their timestamps. The timestamps are shown along the right side of the diagram.* |
+![Graph using PacketClonerCalculator](../images/packet_cloner_calculator.png)  |
+:--------------------------------------------------------------------------: |
+*Each time it receives a packet on its TICK input stream, the PacketClonerCalculator outputs the most recent packet from each of its input streams. The sequence of output packets (bottom) is determined by the sequence of input packets (top) and their timestamps. The timestamps are shown along the right side of the diagram.* |

docs/framework_concepts/framework_concepts.md

@@ -110,3 +110,12 @@ Other policies are also available, implemented using a separate kind of
 component known as an InputStreamHandler.
 
 See [Synchronization](synchronization.md) for more details.
+
+### Real-time streams
+
+MediaPipe calculator graphs are often used to process streams of video or audio
+frames for interactive applications. Normally, each Calculator runs as soon as
+all of its input packets for a given timestamp become available. Calculators
+used in real-time graphs need to define output timestamp bounds based on input
+timestamp bounds in order to allow downstream calculators to be scheduled
+promptly. See [Real-time Streams](realtime_streams.md) for details.

docs/framework_concepts/gpu.md

@@ -66,10 +66,10 @@ calculator derived from base class GlSimpleCalculator. The GPU calculator
 // See GlSimpleCalculator for inputs, outputs and input side packets.
 class LuminanceCalculator : public GlSimpleCalculator {
  public:
-  ::mediapipe::Status GlSetup() override;
-  ::mediapipe::Status GlRender(const GlTexture& src,
-                               const GlTexture& dst) override;
-  ::mediapipe::Status GlTeardown() override;
+  absl::Status GlSetup() override;
+  absl::Status GlRender(const GlTexture& src,
+                        const GlTexture& dst) override;
+  absl::Status GlTeardown() override;
 
  private:
   GLuint program_ = 0;
@@ -77,8 +77,8 @@ class LuminanceCalculator : public GlSimpleCalculator {
 };
 REGISTER_CALCULATOR(LuminanceCalculator);
 
-::mediapipe::Status LuminanceCalculator::GlRender(const GlTexture& src,
-                                                  const GlTexture& dst) {
+absl::Status LuminanceCalculator::GlRender(const GlTexture& src,
+                                           const GlTexture& dst) {
   static const GLfloat square_vertices[] = {
       -1.0f, -1.0f,  // bottom left
       1.0f,  -1.0f,  // bottom right
@@ -128,7 +128,7 @@ REGISTER_CALCULATOR(LuminanceCalculator);
   glDeleteVertexArrays(1, &vao);
   glDeleteBuffers(2, vbo);
 
-  return ::mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 ```
 

docs/framework_concepts/graphs.md

@@ -83,12 +83,12 @@ Below is an example of how to create a subgraph named `TwoPassThroughSubgraph`.
     output_stream: "out3"
 
     node {
-        calculator: "PassThroughculator"
+        calculator: "PassThroughCalculator"
         input_stream: "out1"
         output_stream: "out2"
     }
     node {
-        calculator: "PassThroughculator"
+        calculator: "PassThroughCalculator"
         input_stream: "out2"
         output_stream: "out3"
     }
@@ -219,23 +219,23 @@ packet timestamps 0, 1, 2, 3, ...
 ```c++
 class UnitDelayCalculator : public Calculator {
  public:
-  static ::util::Status FillExpectations(
+  static absl::Status FillExpectations(
       const CalculatorOptions& extendable_options, PacketTypeSet* inputs,
       PacketTypeSet* outputs, PacketTypeSet* input_side_packets) {
     inputs->Index(0)->Set<int>("An integer.");
     outputs->Index(0)->Set<int>("The input delayed by one time unit.");
-    return ::mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  ::util::Status Open() final {
+  absl::Status Open() final {
     Output()->Add(new int(0), Timestamp(0));
-    return ::mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  ::util::Status Process() final {
+  absl::Status Process() final {
     const Packet& packet = Input()->Value();
     Output()->AddPacket(packet.At(packet.Timestamp().NextAllowedInStream()));
-    return ::mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 };
 ```

docs/framework_concepts/packets.md

@@ -12,19 +12,30 @@ nav_order: 3
 {:toc}
 ---
 
-Each calculator is a node of of a graph. We describe how to create a new calculator, how to initialize a calculator, how to perform its calculations, input and output streams, timestamps, and options
+Calculators communicate by sending and receiving packets. Typically a single
+packet is sent along each input stream at each input timestamp. A packet can
+contain any kind of data, such as a single frame of video or a single integer
+detection count.
 
 ## Creating a packet
 
-Packets are generally created with `MediaPipe::Adopt()` (from packet.h).
+Packets are generally created with `mediapipe::MakePacket<T>()` or
+`mediapipe::Adopt()` (from packet.h).
 
 ```c++
-// Create some data.
-auto data = absl::make_unique<MyDataClass>("constructor_argument");
-// Create a packet to own the data.
-Packet p = Adopt(data.release());
+// Create a packet containing some new data.
+Packet p = MakePacket<MyDataClass>("constructor_argument");
 // Make a new packet with the same data and a different timestamp.
 Packet p2 = p.At(Timestamp::PostStream());
 ```
 
+or:
+
+```c++
+// Create some new data.
+auto data = absl::make_unique<MyDataClass>("constructor_argument");
+// Create a packet to own the data.
+Packet p = Adopt(data.release()).At(Timestamp::PostStream());
+```
+
 Data within a packet is accessed with `Packet::Get<T>()`

docs/framework_concepts/realtime_streams.md

@@ -0,0 +1,186 @@
+---
+layout: default
+title: Real-time Streams
+parent: Framework Concepts
+nav_order: 6
+---
+
+# Real-time Streams
+{: .no_toc }
+
+1. TOC
+{:toc}
+---
+
+## Real-time timestamps
+
+MediaPipe calculator graphs are often used to process streams of video or audio
+frames for interactive applications. The MediaPipe framework requires only that
+successive packets be assigned monotonically increasing timestamps. By
+convention, real-time calculators and graphs use the recording time or the
+presentation time of each frame as its timestamp, with each timestamp indicating
+the microseconds since `Jan/1/1970:00:00:00`. This allows packets from various
+sources to be processed in a globally consistent sequence.
+
+## Real-time scheduling
+
+Normally, each Calculator runs as soon as all of its input packets for a given
+timestamp become available. Normally, this happens when the calculator has
+finished processing the previous frame, and each of the calculators producing
+its inputs have finished processing the current frame. The MediaPipe scheduler
+invokes each calculator as soon as these conditions are met. See
+[Synchronization](synchronization.md) for more details.
+
+## Timestamp bounds
+
+When a calculator does not produce any output packets for a given timestamp, it
+can instead output a "timestamp bound" indicating that no packet will be
+produced for that timestamp. This indication is necessary to allow downstream
+calculators to run at that timestamp, even though no packet has arrived for
+certain streams for that timestamp. This is especially important for real-time
+graphs in interactive applications, where it is crucial that each calculator
+begin processing as soon as possible.
+
+Consider a graph like the following:
+
+```
+node {
+   calculator: "A"
+   input_stream: "alpha_in"
+   output_stream: "alpha"
+}
+node {
+   calculator: "B"
+   input_stream: "alpha"
+   input_stream: "foo"
+   output_stream: "beta"
+}
+```
+
+Suppose: at timestamp `T`, node `A` doesn't send a packet in its output stream
+`alpha`. Node `B` gets a packet in `foo` at timestamp `T` and is waiting for a
+packet in `alpha` at timestamp `T`. If `A` doesn't send `B` a timestamp bound
+update for `alpha`, `B` will keep waiting for a packet to arrive in `alpha`.
+Meanwhile, the packet queue of `foo` will accumulate packets at `T`, `T+1` and
+so on.
+
+To output a packet on a stream, a calculator uses the API functions
+`CalculatorContext::Outputs` and `OutputStream::Add`. To instead output a
+timestamp bound on a stream, a calculator can use the API functions
+`CalculatorContext::Outputs` and `CalculatorContext::SetNextTimestampBound`. The
+specified bound is the lowest allowable timestamp for the next packet on the
+specified output stream. When no packet is output, a calculator will typically
+do something like:
+
+```
+cc->Outputs().Tag("output_frame").SetNextTimestampBound(
+  cc->InputTimestamp().NextAllowedInStream());
+```
+
+The function `Timestamp::NextAllowedInStream` returns the successive timestamp.
+For example, `Timestamp(1).NextAllowedInStream() == Timestamp(2)`.
+
+## Propagating timestamp bounds
+
+Calculators that will be used in real-time graphs need to define output
+timestamp bounds based on input timestamp bounds in order to allow downstream
+calculators to be scheduled promptly. A common pattern is for calculators to
+output packets with the same timestamps as their input packets. In this case,
+simply outputting a packet on every call to `Calculator::Process` is sufficient
+to define output timestamp bounds.
+
+However, calculators are not required to follow this common pattern for output
+timestamps, they are only required to choose monotonically increasing output
+timestamps. As a result, certain calculators must calculate timestamp bounds
+explicitly. MediaPipe provides several tools for computing appropriate timestamp
+bound for each calculator.
+
+1\. **SetNextTimestampBound()** can be used to specify the timestamp bound, `t +
+1`, for an output stream.
+
+```
+cc->Outputs.Tag("OUT").SetNextTimestampBound(t.NextAllowedInStream());
+```
+
+Alternatively, an empty packet with timestamp `t` can be produced to specify the
+timestamp bound `t + 1`.
+
+```
+cc->Outputs.Tag("OUT").Add(Packet(), t);
+```
+
+The timestamp bound of an input stream is indicated by the packet or the empty
+packet on the input stream.
+
+```
+Timestamp bound = cc->Inputs().Tag("IN").Value().Timestamp();
+```
+
+2\. **TimestampOffset()** can be specified in order to automatically copy the
+timestamp bound from input streams to output streams.
+
+```
+cc->SetTimestampOffset(0);
+```
+
+This setting has the advantage of propagating timestamp bounds automatically,
+even when only timestamp bounds arrive and Calculator::Process is not invoked.
+
+3\. **ProcessTimestampBounds()** can be specified in order to invoke
+`Calculator::Process` for each new "settled timestamp", where the "settled
+timestamp" is the new highest timestamp below the current timestamp bounds.
+Without `ProcessTimestampBounds()`, `Calculator::Process` is invoked only with
+one or more arriving packets.
+
+```
+cc->SetProcessTimestampBounds(true);
+```
+
+This setting allows a calculator to perform its own timestamp bounds calculation
+and propagation, even when only input timestamps are updated. It can be used to
+replicate the effect of `TimestampOffset()`, but it can also be used to
+calculate a timestamp bound that takes into account additional factors.
+
+For example, in order to replicate `SetTimestampOffset(0)`, a calculator could
+do the following:
+
+```
+absl::Status Open(CalculatorContext* cc) {
+  cc->SetProcessTimestampBounds(true);
+}
+
+absl::Status Process(CalculatorContext* cc) {
+  cc->Outputs.Tag("OUT").SetNextTimestampBound(
+      cc->InputTimestamp().NextAllowedInStream());
+}
+```
+
+## Scheduling of Calculator::Open and Calculator::Close
+
+`Calculator::Open` is invoked when all required input side-packets have been
+produced. Input side-packets can be provided by the enclosing application or by
+"side-packet calculators" inside the graph. Side-packets can be specified from
+outside the graph using the API's `CalculatorGraph::Initialize` and
+`CalculatorGraph::StartRun`. Side packets can be specified by calculators within
+the graph using `CalculatorGraphConfig::OutputSidePackets` and
+`OutputSidePacket::Set`.
+
+Calculator::Close is invoked when all of the input streams have become `Done` by
+being closed or reaching timestamp bound `Timestamp::Done`.
+
+**Note:** If the graph finishes all pending calculator execution and becomes
+`Done`, before some streams become `Done`, then MediaPipe will invoke the
+remaining calls to `Calculator::Close`, so that every calculator can produce its
+final outputs.
+
+The use of `TimestampOffset` has some implications for `Calculator::Close`. A
+calculator specifying `SetTimestampOffset(0)` will by design signal that all of
+its output streams have reached `Timestamp::Done` when all of its input streams
+have reached `Timestamp::Done`, and therefore no further outputs are possible.
+This prevents such a calculator from emitting any packets during
+`Calculator::Close`. If a calculator needs to produce a summary packet during
+`Calculator::Close`, `Calculator::Process` must specify timestamp bounds such
+that at least one timestamp (such as `Timestamp::Max`) remains available during
+`Calculator::Close`. This means that such a calculator normally cannot rely upon
+`SetTimestampOffset(0)` and must instead specify timestamp bounds explicitly
+using `SetNextTimestampBounds()`.

docs/getting_started/android.md

@@ -16,19 +16,21 @@ nav_order: 1
 
 Please follow instructions below to build Android example apps in the supported
 MediaPipe [solutions](../solutions/solutions.md). To learn more about these
-example apps, start from [Hello World! on Android](./hello_world_android.md). To
-incorporate MediaPipe into an existing Android Studio project, see these
-[instructions](./android_archive_library.md) that use Android Archive (AAR) and
-Gradle.
+example apps, start from [Hello World! on Android](./hello_world_android.md).
 
-## Building Android example apps
+To incorporate MediaPipe into Android Studio projects, see these
+[instructions](./android_solutions.md) to use the MediaPipe Android Solution
+APIs (currently in alpha) that are now available in
+[Google's Maven Repository](https://maven.google.com/web/index.html?#com.google.mediapipe).
+
+## Building Android example apps with Bazel
 
 ### Prerequisite
 
 *   Install MediaPipe following these [instructions](./install.md).
 *   Setup Java Runtime.
 *   Setup Android SDK release 28.0.3 and above.
-*   Setup Android NDK r18b and above.
+*   Setup Android NDK version between 18 and 21.
 
 MediaPipe recommends setting up Android SDK and NDK via Android Studio (and see
 below for Android Studio setup). However, if you prefer using MediaPipe without
@@ -51,16 +53,6 @@ $YOUR_INTENDED_API_LEVEL` in android_ndk_repository() and/or
 android_sdk_repository() in the
 [`WORKSPACE`](https://github.com/google/mediapipe/blob/master/WORKSPACE) file.
 
-Please verify all the necessary packages are installed.
-
-*   Android SDK Platform API Level 28 or 29
-*   Android SDK Build-Tools 28 or 29
-*   Android SDK Platform-Tools 28 or 29
-*   Android SDK Tools 26.1.1
-*   Android NDK 17c or above
-
-### Option 1: Build with Bazel in Command Line
-
 Tip: You can run this
 [script](https://github.com/google/mediapipe/blob/master/build_android_examples.sh)
 to build (and install) all MediaPipe Android example apps.
@@ -84,108 +76,3 @@ to build (and install) all MediaPipe Android example apps.
     ```bash
     adb install bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/handtrackinggpu/handtrackinggpu.apk
     ```
-
-### Option 2: Build with Bazel in Android Studio
-
-The MediaPipe project can be imported into Android Studio using the Bazel
-plugins. This allows the MediaPipe examples to be built and modified in Android
-Studio.
-
-To incorporate MediaPipe into an existing Android Studio project, see these
-[instructions](./android_archive_library.md) that use Android Archive (AAR) and
-Gradle.
-
-The steps below use Android Studio 3.5 to build and install a MediaPipe example
-app:
-
-1.  Install and launch Android Studio 3.5.
-
-2.  Select `Configure` -> `SDK Manager` -> `SDK Platforms`.
-
-    *   Verify that Android SDK Platform API Level 28 or 29 is installed.
-    *   Take note of the Android SDK Location, e.g.,
-        `/usr/local/home/Android/Sdk`.
-
-3.  Select `Configure` -> `SDK Manager` -> `SDK Tools`.
-
-    *   Verify that Android SDK Build-Tools 28 or 29 is installed.
-    *   Verify that Android SDK Platform-Tools 28 or 29 is installed.
-    *   Verify that Android SDK Tools 26.1.1 is installed.
-    *   Verify that Android NDK 17c or above is installed.
-    *   Take note of the Android NDK Location, e.g.,
-        `/usr/local/home/Android/Sdk/ndk-bundle` or
-        `/usr/local/home/Android/Sdk/ndk/20.0.5594570`.
-
-4.  Set environment variables `$ANDROID_HOME` and `$ANDROID_NDK_HOME` to point
-    to the installed SDK and NDK.
-
-    ```bash
-    export ANDROID_HOME=/usr/local/home/Android/Sdk
-
-    # If the NDK libraries are installed by a previous version of Android Studio, do
-    export ANDROID_NDK_HOME=/usr/local/home/Android/Sdk/ndk-bundle
-    # If the NDK libraries are installed by Android Studio 3.5, do
-    export ANDROID_NDK_HOME=/usr/local/home/Android/Sdk/ndk/<version number>
-    ```
-
-5.  Select `Configure` -> `Plugins` to install `Bazel`.
-
-6.  On Linux, select `File` -> `Settings` -> `Bazel settings`. On macos, select
-    `Android Studio` -> `Preferences` -> `Bazel settings`. Then, modify `Bazel
-    binary location` to be the same as the output of `$ which bazel`.
-
-7.  Select `Import Bazel Project`.
-
-    *   Select `Workspace`: `/path/to/mediapipe` and select `Next`.
-    *   Select `Generate from BUILD file`: `/path/to/mediapipe/BUILD` and select
-        `Next`.
-    *   Modify `Project View` to be the following and select `Finish`.
-
-    ```
-    directories:
-      # read project settings, e.g., .bazelrc
-      .
-      -mediapipe/objc
-      -mediapipe/examples/ios
-
-    targets:
-      //mediapipe/examples/android/...:all
-      //mediapipe/java/...:all
-
-    android_sdk_platform: android-29
-
-    sync_flags:
-      --host_crosstool_top=@bazel_tools//tools/cpp:toolchain
-    ```
-
-8.  Select `Bazel` -> `Sync` -> `Sync project with Build files`.
-
-    Note: Even after doing step 4, if you still see the error: `"no such package
-    '@androidsdk//': Either the path attribute of android_sdk_repository or the
-    ANDROID_HOME environment variable must be set."`, please modify the
-    [`WORKSPACE`](https://github.com/google/mediapipe/blob/master/WORKSPACE)
-    file to point to your SDK and NDK library locations, as below:
-
-    ```
-    android_sdk_repository(
-        name = "androidsdk",
-        path = "/path/to/android/sdk"
-    )
-
-    android_ndk_repository(
-        name = "androidndk",
-        path = "/path/to/android/ndk"
-    )
-    ```
-
-9.  Connect an Android device to the workstation.
-
-10. Select `Run...` -> `Edit Configurations...`.
-
-    *   Select `Templates` -> `Bazel Command`.
-    *   Enter Target Expression:
-        `//mediapipe/examples/android/src/java/com/google/mediapipe/apps/handtrackinggpu:handtrackinggpu`
-    *   Enter Bazel command: `mobile-install`.
-    *   Enter Bazel flags: `-c opt --config=android_arm64`.
-    *   Press the `[+]` button to add the new configuration.
-    *   Select `Run` to run the example app on the connected Android device.

docs/getting_started/android_archive_library.md

@@ -3,7 +3,7 @@ layout: default
 title: MediaPipe Android Archive
 parent: MediaPipe on Android
 grand_parent: Getting Started
-nav_order: 2
+nav_order: 3
 ---
 
 # MediaPipe Android Archive
@@ -37,7 +37,7 @@ each project.
     load("//mediapipe/java/com/google/mediapipe:mediapipe_aar.bzl", "mediapipe_aar")
 
     mediapipe_aar(
-        name = "mp_face_detection_aar",
+        name = "mediapipe_face_detection",
         calculators = ["//mediapipe/graphs/face_detection:mobile_calculators"],
     )
     ```
@@ -45,25 +45,29 @@ each project.
 2.  Run the Bazel build command to generate the AAR.
 
     ```bash
-    bazel build -c opt --host_crosstool_top=@bazel_tools//tools/cpp:toolchain --fat_apk_cpu=arm64-v8a,armeabi-v7a \
-        //path/to/the/aar/build/file:aar_name
+    bazel build -c opt --strip=ALWAYS \
+        --host_crosstool_top=@bazel_tools//tools/cpp:toolchain \
+        --fat_apk_cpu=arm64-v8a,armeabi-v7a \
+        //path/to/the/aar/build/file:aar_name.aar
     ```
 
-    For the face detection AAR target we made in the step 1, run:
+    For the face detection AAR target we made in step 1, run:
 
     ```bash
-    bazel build -c opt --host_crosstool_top=@bazel_tools//tools/cpp:toolchain --fat_apk_cpu=arm64-v8a,armeabi-v7a \
-        //mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example:mp_face_detection_aar
+    bazel build -c opt --strip=ALWAYS \
+        --host_crosstool_top=@bazel_tools//tools/cpp:toolchain \
+        --fat_apk_cpu=arm64-v8a,armeabi-v7a \
+        //mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example:mediapipe_face_detection.aar
 
     # It should print:
-    # Target //mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example:mp_face_detection_aar up-to-date:
-    # bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mp_face_detection_aar.aar
+    # Target //mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example:mediapipe_face_detection.aar up-to-date:
+    # bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mediapipe_face_detection.aar
     ```
 
 3.  (Optional) Save the AAR to your preferred location.
 
     ```bash
-    cp bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mp_face_detection_aar.aar
+    cp bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mediapipe_face_detection.aar
     /absolute/path/to/your/preferred/location
     ```
 
@@ -74,7 +78,7 @@ each project.
 2.  Copy the AAR into app/libs.
 
     ```bash
-    cp bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mp_face_detection_aar.aar
+    cp bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mediapipe_face_detection.aar
     /path/to/your/app/libs/
     ```
 
@@ -86,36 +90,19 @@ each project.
     Build the MediaPipe binary graph and copy the assets into
     app/src/main/assets, e.g., for the face detection graph, you need to build
     and copy
-    [the binary graph](https://github.com/google/mediapipe/blob/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/facedetectiongpu/BUILD#L41),
-    [the tflite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/face_detection_front.tflite),
+    [the binary graph](https://github.com/google/mediapipe/blob/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/facedetectiongpu/BUILD#L41)
     and
-    [the label map](https://github.com/google/mediapipe/blob/master/mediapipe/models/face_detection_front_labelmap.txt).
+    [the face detection tflite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range.tflite).
 
     ```bash
-    bazel build -c opt mediapipe/mediapipe/graphs/face_detection:mobile_gpu_binary_graph
-    cp bazel-bin/mediapipe/graphs/face_detection/mobile_gpu.binarypb /path/to/your/app/src/main/assets/
-    cp mediapipe/models/face_detection_front.tflite /path/to/your/app/src/main/assets/
-    cp mediapipe/models/face_detection_front_labelmap.txt /path/to/your/app/src/main/assets/
+    bazel build -c opt mediapipe/graphs/face_detection:face_detection_mobile_gpu_binary_graph
+    cp bazel-bin/mediapipe/graphs/face_detection/face_detection_mobile_gpu.binarypb /path/to/your/app/src/main/assets/
+    cp mediapipe/modules/face_detection/face_detection_short_range.tflite /path/to/your/app/src/main/assets/
     ```
 
     ![Screenshot](../images/mobile/assets_location.png)
 
-4.  Make app/src/main/jniLibs and copy OpenCV JNI libraries into
-    app/src/main/jniLibs.
-
-    MediaPipe depends on OpenCV, you will need to copy the precompiled OpenCV so
-    files into app/src/main/jniLibs. You can download the official OpenCV
-    Android SDK from
-    [here](https://github.com/opencv/opencv/releases/download/3.4.3/opencv-3.4.3-android-sdk.zip)
-    and run:
-
-    ```bash
-    cp -R ~/Downloads/OpenCV-android-sdk/sdk/native/libs/arm* /path/to/your/app/src/main/jniLibs/
-    ```
-
-    ![Screenshot](../images/mobile/android_studio_opencv_location.png)
-
-5.  Modify app/build.gradle to add MediaPipe dependencies and MediaPipe AAR.
+4.  Modify app/build.gradle to add MediaPipe dependencies and MediaPipe AAR.
 
     ```
     dependencies {
@@ -126,10 +113,9 @@ each project.
         androidTestImplementation 'androidx.test.ext:junit:1.1.0'
         androidTestImplementation 'androidx.test.espresso:espresso-core:3.1.1'
         // MediaPipe deps
-        implementation 'com.google.flogger:flogger:0.3.1'
-        implementation 'com.google.flogger:flogger-system-backend:0.3.1'
-        implementation 'com.google.code.findbugs:jsr305:3.0.2'
-        implementation 'com.google.guava:guava:27.0.1-android'
+        implementation 'com.google.flogger:flogger:latest.release'
+        implementation 'com.google.flogger:flogger-system-backend:latest.release'
+        implementation 'com.google.code.findbugs:jsr305:latest.release'
         implementation 'com.google.guava:guava:27.0.1-android'
         implementation 'com.google.protobuf:protobuf-java:3.11.4'
         // CameraX core library
@@ -137,10 +123,14 @@ each project.
         implementation "androidx.camera:camera-core:$camerax_version"
         implementation "androidx.camera:camera-camera2:$camerax_version"
         implementation "androidx.camera:camera-lifecycle:$camerax_version"
+        // AutoValue
+        def auto_value_version = "1.8.1"
+        implementation "com.google.auto.value:auto-value-annotations:$auto_value_version"
+        annotationProcessor "com.google.auto.value:auto-value:$auto_value_version"
     }
     ```
 
-6.  Follow our Android app examples to use MediaPipe in Android Studio for your
+5.  Follow our Android app examples to use MediaPipe in Android Studio for your
     use case. If you are looking for an example, a face detection example can be
     found
     [here](https://github.com/jiuqiant/mediapipe_face_detection_aar_example) and

docs/getting_started/android_solutions.md

@@ -0,0 +1,79 @@
+---
+layout: default
+title: Android Solutions
+parent: MediaPipe on Android
+grand_parent: Getting Started
+nav_order: 2
+---
+
+# Android Solution APIs
+{: .no_toc }
+
+1. TOC
+{:toc}
+---
+
+Please follow instructions below to use the MediaPipe Solution APIs in Android
+Studio projects and build the Android example apps in the supported MediaPipe
+[solutions](../solutions/solutions.md).
+
+## Integrate MediaPipe Android Solutions in Android Studio
+
+MediaPipe Android Solution APIs (currently in alpha) are now available in
+[Google's Maven Repository](https://maven.google.com/web/index.html?#com.google.mediapipe).
+To incorporate MediaPipe Android Solutions into an Android Studio project, add
+the following into the project's Gradle dependencies:
+
+```
+dependencies {
+    // MediaPipe solution-core is the foundation of any MediaPipe solutions.
+    implementation 'com.google.mediapipe:solution-core:latest.release'
+    // Optional: MediaPipe Hands solution.
+    implementation 'com.google.mediapipe:hands:latest.release'
+    // Optional: MediaPipe FaceMesh solution.
+    implementation 'com.google.mediapipe:facemesh:latest.release'
+    // MediaPipe deps
+    implementation 'com.google.flogger:flogger:latest.release'
+    implementation 'com.google.flogger:flogger-system-backend:latest.release'
+    implementation 'com.google.guava:guava:27.0.1-android'
+    implementation 'com.google.protobuf:protobuf-java:3.11.4'
+    // CameraX core library
+    def camerax_version = "1.0.0-beta10"
+    implementation "androidx.camera:camera-core:$camerax_version"
+    implementation "androidx.camera:camera-camera2:$camerax_version"
+    implementation "androidx.camera:camera-lifecycle:$camerax_version"
+}
+```
+
+See the detailed solutions API usage examples for different use cases in the
+solution example apps'
+[source code](https://github.com/google/mediapipe/tree/master/mediapipe/examples/android/solutions).
+If the prebuilt maven packages are not sufficient, building the MediaPipe
+Android archive library locally by following these
+[instructions](./android_archive_library.md).
+
+## Build solution example apps in Android Studio
+
+1.  Open Android Studio Arctic Fox on Linux, macOS, or Windows.
+
+2.  Import mediapipe/examples/android/solutions directory into Android Studio.
+
+    ![Screenshot](../images/import_mp_android_studio_project.png)
+
+3.  For Windows users, run `create_win_symlinks.bat` as administrator to create
+    res directory symlinks.
+
+    ![Screenshot](../images/run_create_win_symlinks.png)
+
+4.  Select "File" -> "Sync Project with Gradle Files" to sync project.
+
+5.  Run solution example app in Android Studio.
+
+    ![Screenshot](../images/run_android_solution_app.png)
+
+6.  (Optional) Run solutions on CPU.
+
+    MediaPipe solution example apps run the pipeline and the model inference on
+    GPU by default. If needed, for example to run the apps on Android Emulator,
+    set the `RUN_ON_GPU` boolean variable to `false` in the app's
+    MainActivity.java to run the pipeline and the model inference on CPU.

docs/getting_started/hello_world_android.md

@@ -31,8 +31,8 @@ stream on an Android device.
 
 ## Setup
 
-1.  Install MediaPipe on your system, see [MediaPipe installation guide] for
-    details.
+1.  Install MediaPipe on your system, see
+    [MediaPipe installation guide](./install.md) for details.
 2.  Install Android Development SDK and Android NDK. See how to do so also in
     [MediaPipe installation guide].
 3.  Enable [developer options] on your Android device.
@@ -59,7 +59,7 @@ node: {
   output_stream: "luma_video"
 }
 
-# Applies the Sobel filter to luminance images sotred in RGB format.
+# Applies the Sobel filter to luminance images stored in RGB format.
 node: {
   calculator: "SobelEdgesCalculator"
   input_stream: "luma_video"
@@ -770,7 +770,6 @@ If you ran into any issues, please see the full code of the tutorial
 [`ExternalTextureConverter`]:https://github.com/google/mediapipe/tree/master/mediapipe/java/com/google/mediapipe/components/ExternalTextureConverter.java
 [`FrameLayout`]:https://developer.android.com/reference/android/widget/FrameLayout
 [`FrameProcessor`]:https://github.com/google/mediapipe/tree/master/mediapipe/java/com/google/mediapipe/components/FrameProcessor.java
-[MediaPipe installation guide]:./install.md
 [`PermissionHelper`]: https://github.com/google/mediapipe/tree/master/mediapipe/java/com/google/mediapipe/components/PermissionHelper.java
 [`SurfaceHolder.Callback`]:https://developer.android.com/reference/android/view/SurfaceHolder.Callback.html
 [`SurfaceView`]:https://developer.android.com/reference/android/view/SurfaceView

docs/getting_started/hello_world_cpp.md

@@ -44,7 +44,7 @@ nav_order: 1
     `PrintHelloWorld()` function, defined in a [`CalculatorGraphConfig`] proto.
 
     ```C++
-    ::mediapipe::Status PrintHelloWorld() {
+    absl::Status PrintHelloWorld() {
       // Configures a simple graph, which concatenates 2 PassThroughCalculators.
       CalculatorGraphConfig config = ParseTextProtoOrDie<CalculatorGraphConfig>(R"(
         input_stream: "in"

docs/getting_started/hello_world_ios.md

@@ -31,8 +31,8 @@ stream on an iOS device.
 
 ## Setup
 
-1.  Install MediaPipe on your system, see [MediaPipe installation guide] for
-    details.
+1.  Install MediaPipe on your system, see
+    [MediaPipe installation guide](./install.md) for details.
 2.  Setup your iOS device for development.
 3.  Setup [Bazel] on your system to build and deploy the iOS app.
 
@@ -113,6 +113,10 @@ bazel to build the iOS application. The content of the
 5.  `Main.storyboard` and `Launch.storyboard`
 6.  `Assets.xcassets` directory.
 
+Note: In newer versions of Xcode, you may see additional files `SceneDelegate.h`
+and `SceneDelegate.m`. Make sure to copy them too and add them to the `BUILD`
+file mentioned below.
+
 Copy these files to a directory named `HelloWorld` to a location that can access
 the MediaPipe source code. For example, the source code of the application that
 we will build in this tutorial is located in
@@ -247,6 +251,12 @@ We need to get frames from the `_cameraSource` into our application
 `MPPInputSourceDelegate`. So our application `ViewController` can be a delegate
 of `_cameraSource`.
 
+Update the interface definition of `ViewController` accordingly:
+
+```
+@interface ViewController () <MPPInputSourceDelegate>
+```
+
 To handle camera setup and process incoming frames, we should use a queue
 different from the main queue. Add the following to the implementation block of
 the `ViewController`:
@@ -288,6 +298,12 @@ utility called `MPPLayerRenderer` to display images on the screen. This utility
 can be used to display `CVPixelBufferRef` objects, which is the type of the
 images provided by `MPPCameraInputSource` to its delegates.
 
+In `ViewController.m`, add the following import line:
+
+```
+#import "mediapipe/objc/MPPLayerRenderer.h"
+```
+
 To display images of the screen, we need to add a new `UIView` object called
 `_liveView` to the `ViewController`.
 
@@ -411,6 +427,12 @@ Objective-C++.
 
 ### Use the graph in `ViewController`
 
+In `ViewController.m`, add the following import line:
+
+```
+#import "mediapipe/objc/MPPGraph.h"
+```
+
 Declare a static constant with the name of the graph, the input stream and the
 output stream:
 
@@ -492,6 +514,9 @@ in our app:
     if (![self.mediapipeGraph startWithError:&error]) {
       NSLog(@"Failed to start graph: %@", error);
     }
+    else if (![self.mediapipeGraph waitUntilIdleWithError:&error]) {
+      NSLog(@"Failed to complete graph initial run: %@", error);
+    }
 
     dispatch_async(_videoQueue, ^{
       [_cameraSource start];
@@ -500,8 +525,9 @@ in our app:
 }];
 ```
 
-Note: It is important to start the graph before starting the camera, so that the
-graph is ready to process frames as soon as the camera starts sending them.
+Note: It is important to start the graph before starting the camera and wait
+until completion, so that the graph is ready to process frames as soon as the
+camera starts sending them.
 
 Earlier, when we received frames from the camera in the `processVideoFrame`
 function, we displayed them in the `_liveView` using the `_renderer`. Now, we
@@ -545,6 +571,12 @@ method to receive packets on this output stream and display them on the screen:
 }
 ```
 
+Update the interface definition of `ViewController` with `MPPGraphDelegate`:
+
+```
+@interface ViewController () <MPPGraphDelegate, MPPInputSourceDelegate>
+```
+
 And that is all! Build and run the app on your iOS device. You should see the
 results of running the edge detection graph on a live video feed. Congrats!
 
@@ -556,6 +588,5 @@ appropriate `BUILD` file dependencies for the edge detection graph.
 
 [Bazel]:https://bazel.build/
 [`edge_detection_mobile_gpu.pbtxt`]:https://github.com/google/mediapipe/tree/master/mediapipe/graphs/edge_detection/edge_detection_mobile_gpu.pbtxt
-[MediaPipe installation guide]:./install.md
-[common]:(https://github.com/google/mediapipe/tree/master/mediapipe/examples/ios/common)
-[helloworld]:(https://github.com/google/mediapipe/tree/master/mediapipe/examples/ios/helloworld)
+[common]:https://github.com/google/mediapipe/tree/master/mediapipe/examples/ios/common
+[helloworld]:https://github.com/google/mediapipe/tree/master/mediapipe/examples/ios/helloworld

docs/getting_started/install.md

@@ -25,25 +25,11 @@ install --user six`.
 
 ## Installing on Debian and Ubuntu
 
-1.  Install Bazel.
+1.  Install Bazelisk.
 
     Follow the official
-    [Bazel documentation](https://docs.bazel.build/versions/master/install-ubuntu.html)
-    to install Bazel 3.4 or higher.
-
-    For Nvidia Jetson and Raspberry Pi devices with ARM Ubuntu only, Bazel needs
-    to be built from source:
-
-    ```bash
-    # For Bazel 3.4.0
-    mkdir $HOME/bazel-3.4.0
-    cd $HOME/bazel-3.4.0
-    wget https://github.com/bazelbuild/bazel/releases/download/3.4.0/bazel-3.4.0-dist.zip
-    sudo apt-get install build-essential openjdk-8-jdk python zip unzip
-    unzip bazel-3.4.0-dist.zip
-    env EXTRA_BAZEL_ARGS="--host_javabase=@local_jdk//:jdk" bash ./compile.sh
-    sudo cp output/bazel /usr/local/bin/
-    ```
+    [Bazel documentation](https://docs.bazel.build/versions/master/install-bazelisk.html)
+    to install Bazelisk.
 
 2.  Checkout MediaPipe repository.
 
@@ -57,104 +43,189 @@ install --user six`.
 
 3.  Install OpenCV and FFmpeg.
 
-    Option 1. Use package manager tool to install the pre-compiled OpenCV
-    libraries. FFmpeg will be installed via libopencv-video-dev.
+    **Option 1**. Use package manager tool to install the pre-compiled OpenCV
+    libraries. FFmpeg will be installed via `libopencv-video-dev`.
 
-    Note: Debian 9 and Ubuntu 16.04 provide OpenCV 2.4.9. You may want to take
-    option 2 or 3 to install OpenCV 3 or above.
+    OS                   | OpenCV
+    -------------------- | ------
+    Debian 9 (stretch)   | 2.4
+    Debian 10 (buster)   | 3.2
+    Debian 11 (bullseye) | 4.5
+    Ubuntu 16.04 LTS     | 2.4
+    Ubuntu 18.04 LTS     | 3.2
+    Ubuntu 20.04 LTS     | 4.2
+    Ubuntu 20.04 LTS     | 4.2
+    Ubuntu 21.04         | 4.5
 
     ```bash
-    $ sudo apt-get install libopencv-core-dev libopencv-highgui-dev \
-                           libopencv-calib3d-dev libopencv-features2d-dev \
-                           libopencv-imgproc-dev libopencv-video-dev
+    $ sudo apt-get install -y \
+        libopencv-core-dev \
+        libopencv-highgui-dev \
+        libopencv-calib3d-dev \
+        libopencv-features2d-dev \
+        libopencv-imgproc-dev \
+        libopencv-video-dev
     ```
 
-    Debian 9 and Ubuntu 18.04 install the packages in
-    `/usr/lib/x86_64-linux-gnu`. MediaPipe's [`opencv_linux.BUILD`] and
-    [`ffmpeg_linux.BUILD`] are configured for this library path. Ubuntu 20.04
-    may install the OpenCV and FFmpeg packages in `/usr/local`, Please follow
-    the option 3 below to modify the [`WORKSPACE`], [`opencv_linux.BUILD`] and
-    [`ffmpeg_linux.BUILD`] files accordingly.
-
-    Moreover, for Nvidia Jetson and Raspberry Pi devices with ARM Ubuntu, the
-    library path needs to be modified like the following:
+    MediaPipe's [`opencv_linux.BUILD`] and [`WORKSPACE`] are already configured
+    for OpenCV 2/3 and should work correctly on any architecture:
 
     ```bash
-    sed -i "s/x86_64-linux-gnu/aarch64-linux-gnu/g" third_party/opencv_linux.BUILD
+    # WORKSPACE
+    new_local_repository(
+      name = "linux_opencv",
+      build_file = "@//third_party:opencv_linux.BUILD",
+      path = "/usr",
+    )
+
+    # opencv_linux.BUILD for OpenCV 2/3 installed from Debian package
+    cc_library(
+      name = "opencv",
+      linkopts = [
+        "-l:libopencv_core.so",
+        "-l:libopencv_calib3d.so",
+        "-l:libopencv_features2d.so",
+        "-l:libopencv_highgui.so",
+        "-l:libopencv_imgcodecs.so",
+        "-l:libopencv_imgproc.so",
+        "-l:libopencv_video.so",
+        "-l:libopencv_videoio.so",
+      ],
+    )
     ```
 
-    Option 2. Run [`setup_opencv.sh`] to automatically build OpenCV from source
-    and modify MediaPipe's OpenCV config.
+    For OpenCV 4 you need to modify [`opencv_linux.BUILD`] taking into account
+    current architecture:
 
-    Option 3. Follow OpenCV's
+    ```bash
+    # WORKSPACE
+    new_local_repository(
+      name = "linux_opencv",
+      build_file = "@//third_party:opencv_linux.BUILD",
+      path = "/usr",
+    )
+
+    # opencv_linux.BUILD for OpenCV 4 installed from Debian package
+    cc_library(
+      name = "opencv",
+      hdrs = glob([
+        # Uncomment according to your multiarch value (gcc -print-multiarch):
+        #  "include/aarch64-linux-gnu/opencv4/opencv2/cvconfig.h",
+        #  "include/arm-linux-gnueabihf/opencv4/opencv2/cvconfig.h",
+        #  "include/x86_64-linux-gnu/opencv4/opencv2/cvconfig.h",
+        "include/opencv4/opencv2/**/*.h*",
+      ]),
+      includes = [
+        # Uncomment according to your multiarch value (gcc -print-multiarch):
+        #  "include/aarch64-linux-gnu/opencv4/",
+        #  "include/arm-linux-gnueabihf/opencv4/",
+        #  "include/x86_64-linux-gnu/opencv4/",
+        "include/opencv4/",
+      ],
+      linkopts = [
+        "-l:libopencv_core.so",
+        "-l:libopencv_calib3d.so",
+        "-l:libopencv_features2d.so",
+        "-l:libopencv_highgui.so",
+        "-l:libopencv_imgcodecs.so",
+        "-l:libopencv_imgproc.so",
+        "-l:libopencv_video.so",
+        "-l:libopencv_videoio.so",
+      ],
+    )
+    ```
+
+    **Option 2**. Run [`setup_opencv.sh`] to automatically build OpenCV from
+    source and modify MediaPipe's OpenCV config. This option will do all steps
+    defined in Option 3 automatically.
+
+    **Option 3**. Follow OpenCV's
     [documentation](https://docs.opencv.org/3.4.6/d7/d9f/tutorial_linux_install.html)
     to manually build OpenCV from source code.
 
-    Note: You may need to modify [`WORKSPACE`], [`opencv_linux.BUILD`] and
-    [`ffmpeg_linux.BUILD`] to point MediaPipe to your own OpenCV and FFmpeg
-    libraries. For example if OpenCV and FFmpeg are both manually installed in
-    "/usr/local/", you will need to update: (1) the "linux_opencv" and
-    "linux_ffmpeg" new_local_repository rules in [`WORKSPACE`], (2) the "opencv"
-    cc_library rule in [`opencv_linux.BUILD`], and (3) the "libffmpeg"
-    cc_library rule in [`ffmpeg_linux.BUILD`]. These 3 changes are shown below:
+    You may need to modify [`WORKSPACE`] and [`opencv_linux.BUILD`] to point
+    MediaPipe to your own OpenCV libraries. Assume OpenCV would be installed to
+    `/usr/local/` which is recommended by default.
+
+    OpenCV 2/3 setup:
 
     ```bash
+    # WORKSPACE
     new_local_repository(
-        name = "linux_opencv",
-        build_file = "@//third_party:opencv_linux.BUILD",
-        path = "/usr/local",
+      name = "linux_opencv",
+      build_file = "@//third_party:opencv_linux.BUILD",
+      path = "/usr/local",
     )
 
+    # opencv_linux.BUILD for OpenCV 2/3 installed to /usr/local
+    cc_library(
+      name = "opencv",
+      linkopts = [
+        "-L/usr/local/lib",
+        "-l:libopencv_core.so",
+        "-l:libopencv_calib3d.so",
+        "-l:libopencv_features2d.so",
+        "-l:libopencv_highgui.so",
+        "-l:libopencv_imgcodecs.so",
+        "-l:libopencv_imgproc.so",
+        "-l:libopencv_video.so",
+        "-l:libopencv_videoio.so",
+      ],
+    )
+    ```
+
+    OpenCV 4 setup:
+
+    ```bash
+    # WORKSPACE
     new_local_repository(
-        name = "linux_ffmpeg",
-        build_file = "@//third_party:ffmpeg_linux.BUILD",
-        path = "/usr/local",
+      name = "linux_opencv",
+      build_file = "@//third_party:opencv_linux.BUILD",
+      path = "/usr/local",
     )
 
+    # opencv_linux.BUILD for OpenCV 4 installed to /usr/local
     cc_library(
-        name = "opencv",
-        srcs = glob(
-            [
-                "lib/libopencv_core.so",
-                "lib/libopencv_highgui.so",
-                "lib/libopencv_imgcodecs.so",
-                "lib/libopencv_imgproc.so",
-                "lib/libopencv_video.so",
-                "lib/libopencv_videoio.so",
-            ],
-        ),
-        hdrs = glob([
-            # For OpenCV 3.x
-            "include/opencv2/**/*.h*",
-            # For OpenCV 4.x
-            # "include/opencv4/opencv2/**/*.h*",
-        ]),
-        includes = [
-            # For OpenCV 3.x
-            "include/",
-            # For OpenCV 4.x
-            # "include/opencv4/",
-        ],
-        linkstatic = 1,
-        visibility = ["//visibility:public"],
+      name = "opencv",
+      hdrs = glob([
+        "include/opencv4/opencv2/**/*.h*",
+      ]),
+      includes = [
+        "include/opencv4/",
+      ],
+      linkopts = [
+        "-L/usr/local/lib",
+        "-l:libopencv_core.so",
+        "-l:libopencv_calib3d.so",
+        "-l:libopencv_features2d.so",
+        "-l:libopencv_highgui.so",
+        "-l:libopencv_imgcodecs.so",
+        "-l:libopencv_imgproc.so",
+        "-l:libopencv_video.so",
+        "-l:libopencv_videoio.so",
+      ],
+    )
+    ```
+
+    Current FFmpeg setup is defined in [`ffmpeg_linux.BUILD`] and should work
+    for any architecture:
+
+    ```bash
+    # WORKSPACE
+    new_local_repository(
+      name = "linux_ffmpeg",
+      build_file = "@//third_party:ffmpeg_linux.BUILD",
+      path = "/usr"
     )
 
+    # ffmpeg_linux.BUILD for FFmpeg installed from Debian package
     cc_library(
-        name = "libffmpeg",
-        srcs = glob(
-            [
-                "lib/libav*.so",
-            ],
-        ),
-        hdrs = glob(["include/libav*/*.h"]),
-        includes = ["include"],
-        linkopts = [
-            "-lavcodec",
-            "-lavformat",
-            "-lavutil",
-        ],
-        linkstatic = 1,
-        visibility = ["//visibility:public"],
+      name = "libffmpeg",
+      linkopts = [
+        "-l:libavcodec.so",
+        "-l:libavformat.so",
+        "-l:libavutil.so",
+      ],
     )
     ```
 
@@ -207,11 +278,11 @@ build issues.
 
 **Disclaimer**: Running MediaPipe on CentOS is experimental.
 
-1.  Install Bazel.
+1.  Install Bazelisk.
 
     Follow the official
-    [Bazel documentation](https://docs.bazel.build/versions/master/install-redhat.html)
-    to install Bazel 3.4 or higher.
+    [Bazel documentation](https://docs.bazel.build/versions/master/install-bazelisk.html)
+    to install Bazelisk.
 
 2.  Checkout MediaPipe repository.
 
@@ -336,18 +407,11 @@ build issues.
     *   Install [Xcode](https://developer.apple.com/xcode/) and its Command Line
         Tools by `xcode-select --install`.
 
-2.  Install Bazel.
+2.  Install Bazelisk.
 
-    Option 1. Use package manager tool to install Bazel
-
-    ```bash
-    $ brew install bazel
-    # Run 'bazel version' to check version of bazel
-    ```
-
-    Option 2. Follow the official
-    [Bazel documentation](https://docs.bazel.build/versions/master/install-os-x.html#install-with-installer-mac-os-x)
-    to install Bazel 3.4 or higher.
+    Follow the official
+    [Bazel documentation](https://docs.bazel.build/versions/master/install-bazelisk.html)
+    to install Bazelisk.
 
 3.  Checkout MediaPipe repository.
 
@@ -360,7 +424,7 @@ build issues.
 4.  Install OpenCV and FFmpeg.
 
     Option 1. Use HomeBrew package manager tool to install the pre-compiled
-    OpenCV 3.4.5 libraries. FFmpeg will be installed via OpenCV.
+    OpenCV 3 libraries. FFmpeg will be installed via OpenCV.
 
     ```bash
     $ brew install opencv@3
@@ -491,29 +555,36 @@ next section.
 
 4.  Install Visual C++ Build Tools 2019 and WinSDK
 
-    Go to https://visualstudio.microsoft.com/visual-cpp-build-tools, download
-    build tools, and install Microsoft Visual C++ 2019 Redistributable and
-    Microsoft Build Tools 2019.
+    Go to
+    [the VisualStudio website](https://visualstudio.microsoft.com/visual-cpp-build-tools),
+    download build tools, and install Microsoft Visual C++ 2019 Redistributable
+    and Microsoft Build Tools 2019.
 
     Download the WinSDK from
-    https://developer.microsoft.com/en-us/windows/downloads/windows-10-sdk/ and
-    install.
+    [the official MicroSoft website](https://developer.microsoft.com/en-us/windows/downloads/windows-10-sdk/)
+    and install.
 
-5.  Install Bazel and add the location of the Bazel executable to the `%PATH%`
-    environment variable.
+5.  Install Bazel or Bazelisk and add the location of the Bazel executable to
+    the `%PATH%` environment variable.
 
-    Follow the official
-    [Bazel documentation](https://docs.bazel.build/versions/master/install-windows.html)
-    to install Bazel 3.4 or higher.
+    Option 1. Follow
+    [the official Bazel documentation](https://docs.bazel.build/versions/master/install-windows.html)
+    to install Bazel 3.7.2 or higher.
 
-6.  Set Bazel variables.
+    Option 2. Follow the official
+    [Bazel documentation](https://docs.bazel.build/versions/master/install-bazelisk.html)
+    to install Bazelisk.
+
+6.  Set Bazel variables. Learn more details about
+    ["Build on Windows"](https://docs.bazel.build/versions/master/windows.html#build-c-with-msvc)
+    in the Bazel official documentation.
 
     ```
-    # Find the exact paths and version numbers from your local version.
+    # Please find the exact paths and version numbers from your local version.
     C:\> set BAZEL_VS=C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools
     C:\> set BAZEL_VC=C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC
-    C:\> set BAZEL_VC_FULL_VERSION=14.25.28610
-    C:\> set BAZEL_WINSDK_FULL_VERSION=10.1.18362.1
+    C:\> set BAZEL_VC_FULL_VERSION=<Your local VC version>
+    C:\> set BAZEL_WINSDK_FULL_VERSION=<Your local WinSDK version>
     ```
 
 7.  Checkout MediaPipe repository.
@@ -600,19 +671,11 @@ cameras. Alternatively, you use a video file as input.
     username@DESKTOP-TMVLBJ1:~$ sudo apt-get update && sudo apt-get install -y build-essential git python zip adb openjdk-8-jdk
     ```
 
-5.  Install Bazel.
+5.  Install Bazelisk.
 
-    ```bash
-    username@DESKTOP-TMVLBJ1:~$ curl -sLO --retry 5 --retry-max-time 10 \
-    https://storage.googleapis.com/bazel/3.4.0/release/bazel-3.4.0-installer-linux-x86_64.sh && \
-    sudo mkdir -p /usr/local/bazel/3.4.0 && \
-    chmod 755 bazel-3.4.0-installer-linux-x86_64.sh && \
-    sudo ./bazel-3.4.0-installer-linux-x86_64.sh --prefix=/usr/local/bazel/3.4.0 && \
-    source /usr/local/bazel/3.4.0/lib/bazel/bin/bazel-complete.bash
-
-    username@DESKTOP-TMVLBJ1:~$ /usr/local/bazel/3.4.0/lib/bazel/bin/bazel version && \
-    alias bazel='/usr/local/bazel/3.4.0/lib/bazel/bin/bazel'
-    ```
+    Follow the official
+    [Bazel documentation](https://docs.bazel.build/versions/master/install-bazelisk.html)
+    to install Bazelisk.
 
 6.  Checkout MediaPipe repository.
 
@@ -733,7 +796,7 @@ This will use a Docker image that will isolate mediapipe's installation from the
     ```bash
     $ docker run -it --name mediapipe mediapipe:latest
 
-    root@bca08b91ff63:/mediapipe# GLOG_logtostderr=1 bazel run --define MEDIAPIPE_DISABLE_GPU=1 mediapipe/examples/desktop/hello_world:hello_world
+    root@bca08b91ff63:/mediapipe# GLOG_logtostderr=1 bazelisk run --define MEDIAPIPE_DISABLE_GPU=1 mediapipe/examples/desktop/hello_world:hello_world
 
     # Should print:
     # Hello World!
@@ -760,7 +823,7 @@ common build issues.
     root@bca08b91ff63:/mediapipe# bash ./setup_android_sdk_and_ndk.sh
 
     # Should print:
-    # Android NDK is now installed. Consider setting $ANDROID_NDK_HOME environment variable to be /root/Android/Sdk/ndk-bundle/android-ndk-r18b
+    # Android NDK is now installed. Consider setting $ANDROID_NDK_HOME environment variable to be /root/Android/Sdk/ndk-bundle/android-ndk-r19c
     # Set android_ndk_repository and android_sdk_repository in WORKSPACE
     # Done
 

docs/getting_started/javascript.md

@@ -16,16 +16,29 @@ nav_order: 4
 
 MediaPipe currently offers the following solutions:
 
-Solution          | NPM Package                   | Example
------------------ | ----------------------------- | -------
-[Face Mesh][F-pg] | [@mediapipe/face_mesh][F-npm] | [mediapipe.dev/demo/face_mesh][F-demo]
-[Hands][H-pg]     | [@mediapipe/hands][H-npm]     | [mediapipe.dev/demo/hands][H-demo]
-[Pose][P-pg]      | [@mediapipe/pose][P-npm]      | [mediapipe.dev/demo/pose][P-demo]
-[Holistic][Ho-pg] | [@mediapipe/holistic][Ho-npm] | [mediapipe.dev/demo/holistic][Ho-demo]
+Solution                    | NPM Package                             | Example
+--------------------------- | --------------------------------------- | -------
+[Face Mesh][F-pg]           | [@mediapipe/face_mesh][F-npm]           | [mediapipe.dev/demo/face_mesh][F-demo]
+[Face Detection][Fd-pg]     | [@mediapipe/face_detection][Fd-npm]     | [mediapipe.dev/demo/face_detection][Fd-demo]
+[Hands][H-pg]               | [@mediapipe/hands][H-npm]               | [mediapipe.dev/demo/hands][H-demo]
+[Holistic][Ho-pg]           | [@mediapipe/holistic][Ho-npm]           | [mediapipe.dev/demo/holistic][Ho-demo]
+[Objectron][Ob-pg]          | [@mediapipe/objectron][Ob-npm]          | [mediapipe.dev/demo/objectron][Ob-demo]
+[Pose][P-pg]                | [@mediapipe/pose][P-npm]                | [mediapipe.dev/demo/pose][P-demo]
+[Selfie Segmentation][S-pg] | [@mediapipe/selfie_segmentation][S-npm] | [mediapipe.dev/demo/selfie_segmentation][S-demo]
 
 Click on a solution link above for more information, including API and code
 snippets.
 
+### Supported plaforms:
+
+| Browser | Platform                | Notes                                  |
+| ------- | ----------------------- | -------------------------------------- |
+| Chrome  | Android / Windows / Mac | Pixel 4 and older unsupported. Fuschia |
+|         |                         | unsupported.                           |
+| Chrome  | iOS                     | Camera unavailable in Chrome on iOS.   |
+| Safari  | iPad/iPhone/Mac         | iOS and Safari on iPad / iPhone /      |
+|         |                         | MacBook                                |
+
 The quickest way to get acclimated is to look at the examples above. Each demo
 has a link to a [CodePen][codepen] so that you can edit the code and try it
 yourself. We have included a number of utility packages to help you get started:
@@ -63,26 +76,27 @@ affecting your work, restrict your request to a `<minor>` number. e.g.,
 
 [Ho-pg]: ../solutions/holistic#javascript-solution-api
 [F-pg]: ../solutions/face_mesh#javascript-solution-api
+[Fd-pg]: ../solutions/face_detection#javascript-solution-api
 [H-pg]: ../solutions/hands#javascript-solution-api
+[Ob-pg]: ../solutions/objectron#javascript-solution-api
 [P-pg]: ../solutions/pose#javascript-solution-api
+[S-pg]: ../solutions/selfie_segmentation#javascript-solution-api
 [Ho-npm]: https://www.npmjs.com/package/@mediapipe/holistic
 [F-npm]: https://www.npmjs.com/package/@mediapipe/face_mesh
+[Fd-npm]: https://www.npmjs.com/package/@mediapipe/face_detection
 [H-npm]: https://www.npmjs.com/package/@mediapipe/hands
+[Ob-npm]: https://www.npmjs.com/package/@mediapipe/objectron
 [P-npm]: https://www.npmjs.com/package/@mediapipe/pose
-[draw-npm]: https://www.npmjs.com/package/@mediapipe/pose
-[cam-npm]: https://www.npmjs.com/package/@mediapipe/pose
-[ctrl-npm]: https://www.npmjs.com/package/@mediapipe/pose
-[Ho-jsd]: https://www.jsdelivr.com/package/npm/@mediapipe/holistic
-[F-jsd]: https://www.jsdelivr.com/package/npm/@mediapipe/face_mesh
-[H-jsd]: https://www.jsdelivr.com/package/npm/@mediapipe/hands
-[P-jsd]: https://www.jsdelivr.com/package/npm/@mediapipe/pose
-[Ho-pen]: https://code.mediapipe.dev/codepen/holistic
-[F-pen]: https://code.mediapipe.dev/codepen/face_mesh
-[H-pen]: https://code.mediapipe.dev/codepen/hands
-[P-pen]: https://code.mediapipe.dev/codepen/pose
+[S-npm]: https://www.npmjs.com/package/@mediapipe/selfie_segmentation
+[draw-npm]: https://www.npmjs.com/package/@mediapipe/drawing_utils
+[cam-npm]: https://www.npmjs.com/package/@mediapipe/camera_utils
+[ctrl-npm]: https://www.npmjs.com/package/@mediapipe/control_utils
 [Ho-demo]: https://mediapipe.dev/demo/holistic
 [F-demo]: https://mediapipe.dev/demo/face_mesh
+[Fd-demo]: https://mediapipe.dev/demo/face_detection
 [H-demo]: https://mediapipe.dev/demo/hands
+[Ob-demo]: https://mediapipe.dev/demo/objectron
 [P-demo]: https://mediapipe.dev/demo/pose
+[S-demo]: https://mediapipe.dev/demo/selfie_segmentation
 [npm]: https://www.npmjs.com/package/@mediapipe
 [codepen]: https://code.mediapipe.dev/codepen

docs/getting_started/python.md

@@ -26,7 +26,7 @@ You can, for instance, activate a Python virtual environment:
 $ python3 -m venv mp_env && source mp_env/bin/activate
 ```
 
-Install MediaPipe Python package and start Python intepreter:
+Install MediaPipe Python package and start Python interpreter:
 
 ```bash
 (mp_env)$ pip install mediapipe
@@ -45,17 +45,25 @@ Tip: Use command `deactivate` to later exit the Python virtual environment.
 To learn more about configuration options and usage examples, please find
 details in each solution via the links below:
 
+*   [MediaPipe Face Detection](../solutions/face_detection#python-solution-api)
 *   [MediaPipe Face Mesh](../solutions/face_mesh#python-solution-api)
 *   [MediaPipe Hands](../solutions/hands#python-solution-api)
-*   [MediaPipe Pose](../solutions/pose#python-solution-api)
 *   [MediaPipe Holistic](../solutions/holistic#python-solution-api)
+*   [MediaPipe Objectron](../solutions/objectron#python-solution-api)
+*   [MediaPipe Pose](../solutions/pose#python-solution-api)
+*   [MediaPipe Selfie Segmentation](../solutions/selfie_segmentation#python-solution-api)
 
 ## MediaPipe on Google Colab
 
+*   [MediaPipe Face Detection Colab](https://mediapipe.page.link/face_detection_py_colab)
 *   [MediaPipe Face Mesh Colab](https://mediapipe.page.link/face_mesh_py_colab)
 *   [MediaPipe Hands Colab](https://mediapipe.page.link/hands_py_colab)
-*   [MediaPipe Pose Colab](https://mediapipe.page.link/pose_py_colab)
 *   [MediaPipe Holistic Colab](https://mediapipe.page.link/holistic_py_colab)
+*   [MediaPipe Objectron Colab](https://mediapipe.page.link/objectron_py_colab)
+*   [MediaPipe Pose Colab](https://mediapipe.page.link/pose_py_colab)
+*   [MediaPipe Pose Classification Colab (Basic)](https://mediapipe.page.link/pose_classification_basic)
+*   [MediaPipe Pose Classification Colab (Extended)](https://mediapipe.page.link/pose_classification_extended)
+*   [MediaPipe Selfie Segmentation Colab](https://mediapipe.page.link/selfie_segmentation_py_colab)
 
 ## MediaPipe Python Framework
 
@@ -70,6 +78,11 @@ Python package from source. Otherwise, we strongly encourage our users to simply
 run `pip install mediapipe` to use the ready-to-use solutions, more convenient
 and much faster.
 
+MediaPipe PyPI currently doesn't provide aarch64 Python wheel
+files. For building and using MediaPipe Python on aarch64 Linux systems such as
+Nvidia Jetson and Raspberry Pi, please read
+[here](https://github.com/jiuqiant/mediapipe-python-aarch64).
+
 1.  Make sure that Bazel and OpenCV are correctly installed and configured for
     MediaPipe. Please see [Installation](./install.md) for how to setup Bazel
     and OpenCV for MediaPipe on Linux and macOS.
@@ -82,12 +95,18 @@ and much faster.
     $ sudo apt install python3-dev
     $ sudo apt install python3-venv
     $ sudo apt install -y protobuf-compiler
+
+    # If you need to build opencv from source.
+    $ sudo apt install cmake
     ```
 
     macOS:
 
     ```bash
     $ brew install protobuf
+
+    # If you need to build opencv from source.
+    $ brew install cmake
     ```
 
     Windows:
@@ -118,3 +137,10 @@ and much faster.
     (mp_env)mediapipe$ python3 setup.py gen_protos
     (mp_env)mediapipe$ python3 setup.py install --link-opencv
     ```
+
+    or
+
+    ```bash
+    (mp_env)mediapipe$ python3 setup.py gen_protos
+    (mp_env)mediapipe$ python3 setup.py bdist_wheel
+    ```

docs/getting_started/python_framework.md

@@ -74,7 +74,7 @@ Mapping\[str, Packet\]               | std::map<std::string, Packet> | create_st
 np.ndarray<br>(cv.mat and PIL.Image) | mp::ImageFrame                | create_image_frame(<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;format=ImageFormat.SRGB,<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;data=mat) | get_image_frame(packet)
 np.ndarray                           | mp::Matrix                    | create_matrix(data)                                                                                                                                          | get_matrix(packet)
 Google Proto Message                 | Google Proto Message          | create_proto(proto)                                                                                                                                          | get_proto(packet)
-List\[Proto\]                        | std::vector\<Proto\>          | create_proto_vector(proto_list)                                                                                                                              | get_proto_list(packet)
+List\[Proto\]                        | std::vector\<Proto\>          | n/a                                                                                                                                                          | get_proto_list(packet)
 
 It's not uncommon that users create custom C++ classes and and send those into
 the graphs and calculators. To allow the custom classes to be used in Python

docs/getting_started/troubleshooting.md

@@ -97,6 +97,49 @@ linux_opencv/macos_opencv/windows_opencv.BUILD files for your local opencv
 libraries. [This GitHub issue](https://github.com/google/mediapipe/issues/666)
 may also help.
 
+## Python pip install failure
+
+The error message:
+
+```
+ERROR: Could not find a version that satisfies the requirement mediapipe
+ERROR: No matching distribution found for mediapipe
+```
+
+after running `pip install mediapipe` usually indicates that there is no qualified MediaPipe Python for your system.
+Please note that MediaPipe Python PyPI officially supports the **64-bit**
+version of Python 3.7 and above on the following OS:
+
+-   x86_64 Linux
+-   x86_64 macOS 10.15+
+-   amd64 Windows
+
+If the OS is currently supported and you still see this error, please make sure
+that both the Python and pip binary are for Python 3.7 and above. Otherwise,
+please consider building the MediaPipe Python package locally by following the
+instructions [here](python.md#building-mediapipe-python-package).
+
+## Python DLL load failure on Windows
+
+The error message:
+
+```
+ImportError: DLL load failed: The specified module could not be found
+```
+
+usually indicates that the local Windows system is missing Visual C++
+redistributable packages and/or Visual C++ runtime DLLs. This can be solved by
+either installing the official
+[vc_redist.x64.exe](https://support.microsoft.com/en-us/topic/the-latest-supported-visual-c-downloads-2647da03-1eea-4433-9aff-95f26a218cc0)
+or installing the "msvc-runtime" Python package by running
+
+```bash
+$ python -m pip install msvc-runtime
+```
+
+Please note that the "msvc-runtime" Python package is not released or maintained
+by Microsoft.
+
 ## Native method not found
 
 The error message:

docs/index.md

@@ -34,17 +34,18 @@ Hair Segmentation
 
 []()                                                                                      | [Android](https://google.github.io/mediapipe/getting_started/android) | [iOS](https://google.github.io/mediapipe/getting_started/ios) | [C++](https://google.github.io/mediapipe/getting_started/cpp) | [Python](https://google.github.io/mediapipe/getting_started/python) | [JS](https://google.github.io/mediapipe/getting_started/javascript) | [Coral](https://github.com/google/mediapipe/tree/master/mediapipe/examples/coral/README.md)
 :---------------------------------------------------------------------------------------- | :-------------------------------------------------------------: | :-----------------------------------------------------: | :-----------------------------------------------------: | :-----------------------------------------------------------: | :-----------------------------------------------------------: | :--------------------------------------------------------------------:
-[Face Detection](https://google.github.io/mediapipe/solutions/face_detection)                   | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               | ✅
+[Face Detection](https://google.github.io/mediapipe/solutions/face_detection)                   | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             | ✅
 [Face Mesh](https://google.github.io/mediapipe/solutions/face_mesh)                             | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Iris](https://google.github.io/mediapipe/solutions/iris)                                       | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               |
 [Hands](https://google.github.io/mediapipe/solutions/hands)                                     | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Pose](https://google.github.io/mediapipe/solutions/pose)                                       | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Holistic](https://google.github.io/mediapipe/solutions/holistic)                               | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
+[Selfie Segmentation](https://google.github.io/mediapipe/solutions/selfie_segmentation)         | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Hair Segmentation](https://google.github.io/mediapipe/solutions/hair_segmentation)             | ✅                                                               |                                                         | ✅                                                       |                                                               |                                                               |
 [Object Detection](https://google.github.io/mediapipe/solutions/object_detection)               | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               | ✅
 [Box Tracking](https://google.github.io/mediapipe/solutions/box_tracking)                       | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               |
 [Instant Motion Tracking](https://google.github.io/mediapipe/solutions/instant_motion_tracking) | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
-[Objectron](https://google.github.io/mediapipe/solutions/objectron)                             | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
+[Objectron](https://google.github.io/mediapipe/solutions/objectron)                             | ✅                                                               |                                                         | ✅                                                       | ✅                                                             | ✅                                                             |
 [KNIFT](https://google.github.io/mediapipe/solutions/knift)                                     | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
 [AutoFlip](https://google.github.io/mediapipe/solutions/autoflip)                               |                                                                 |                                                         | ✅                                                       |                                                               |                                                               |
 [MediaSequence](https://google.github.io/mediapipe/solutions/media_sequence)                    |                                                                 |                                                         | ✅                                                       |                                                               |                                                               |
@@ -54,46 +55,22 @@ See also
 [MediaPipe Models and Model Cards](https://google.github.io/mediapipe/solutions/models)
 for ML models released in MediaPipe.
 
-## MediaPipe in Python
-
-MediaPipe offers customizable Python solutions as a prebuilt Python package on
-[PyPI](https://pypi.org/project/mediapipe/), which can be installed simply with
-`pip install mediapipe`. It also provides tools for users to build their own
-solutions. Please see
-[MediaPipe in Python](https://google.github.io/mediapipe/getting_started/python)
-for more info.
-
-## MediaPipe on the Web
-
-MediaPipe on the Web is an effort to run the same ML solutions built for mobile
-and desktop also in web browsers. The official API is under construction, but
-the core technology has been proven effective. Please see
-[MediaPipe on the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html)
-in Google Developers Blog for details.
-
-You can use the following links to load a demo in the MediaPipe Visualizer, and
-over there click the "Runner" icon in the top bar like shown below. The demos
-use your webcam video as input, which is processed all locally in real-time and
-never leaves your device.
-
-![visualizer_runner](images/visualizer_runner.png)
-
-*   [MediaPipe Face Detection](https://viz.mediapipe.dev/demo/face_detection)
-*   [MediaPipe Iris](https://viz.mediapipe.dev/demo/iris_tracking)
-*   [MediaPipe Iris: Depth-from-Iris](https://viz.mediapipe.dev/demo/iris_depth)
-*   [MediaPipe Hands](https://viz.mediapipe.dev/demo/hand_tracking)
-*   [MediaPipe Hands (palm/hand detection only)](https://viz.mediapipe.dev/demo/hand_detection)
-*   [MediaPipe Pose](https://viz.mediapipe.dev/demo/pose_tracking)
-*   [MediaPipe Hair Segmentation](https://viz.mediapipe.dev/demo/hair_segmentation)
-
 ## Getting started
 
-Learn how to [install](https://google.github.io/mediapipe/getting_started/install)
-MediaPipe and
-[build example applications](https://google.github.io/mediapipe/getting_started/building_examples),
-and start exploring our ready-to-use
-[solutions](https://google.github.io/mediapipe/solutions/solutions) that you can
-further extend and customize.
+To start using MediaPipe
+[solutions](https://google.github.io/mediapipe/solutions/solutions) with only a few
+lines code, see example code and demos in
+[MediaPipe in Python](https://google.github.io/mediapipe/getting_started/python) and
+[MediaPipe in JavaScript](https://google.github.io/mediapipe/getting_started/javascript).
+
+To use MediaPipe in C++, Android and iOS, which allow further customization of
+the [solutions](https://google.github.io/mediapipe/solutions/solutions) as well as
+building your own, learn how to
+[install](https://google.github.io/mediapipe/getting_started/install) MediaPipe and
+start building example applications in
+[C++](https://google.github.io/mediapipe/getting_started/cpp),
+[Android](https://google.github.io/mediapipe/getting_started/android) and
+[iOS](https://google.github.io/mediapipe/getting_started/ios).
 
 The source code is hosted in the
 [MediaPipe Github repository](https://github.com/google/mediapipe), and you can
@@ -102,6 +79,15 @@ run code search using
 
 ## Publications
 
+*   [Bringing artworks to life with AR](https://developers.googleblog.com/2021/07/bringing-artworks-to-life-with-ar.html)
+    in Google Developers Blog
+*   [Prosthesis control via Mirru App using MediaPipe hand tracking](https://developers.googleblog.com/2021/05/control-your-mirru-prosthesis-with-mediapipe-hand-tracking.html)
+    in Google Developers Blog
+*   [SignAll SDK: Sign language interface using MediaPipe is now available for
+    developers](https://developers.googleblog.com/2021/04/signall-sdk-sign-language-interface-using-mediapipe-now-available.html)
+    in Google Developers Blog
+*   [MediaPipe Holistic - Simultaneous Face, Hand and Pose Prediction, on Device](https://ai.googleblog.com/2020/12/mediapipe-holistic-simultaneous-face.html)
+    in Google AI Blog
 *   [Background Features in Google Meet, Powered by Web ML](https://ai.googleblog.com/2020/10/background-features-in-google-meet.html)
     in Google AI Blog
 *   [MediaPipe 3D Face Transform](https://developers.googleblog.com/2020/09/mediapipe-3d-face-transform.html)

docs/solutions/autoflip.md

@@ -2,7 +2,7 @@
 layout: default
 title: AutoFlip (Saliency-aware Video Cropping)
 parent: Solutions
-nav_order: 13
+nav_order: 14
 ---
 
 # AutoFlip: Saliency-aware Video Cropping

docs/solutions/box_tracking.md

@@ -2,7 +2,7 @@
 layout: default
 title: Box Tracking
 parent: Solutions
-nav_order: 9
+nav_order: 10
 ---
 
 # MediaPipe Box Tracking

docs/solutions/face_detection.md

@@ -39,6 +39,183 @@ section.
 
 ![face_detection_android_gpu.gif](../images/mobile/face_detection_android_gpu.gif)
 
+## Solution APIs
+
+### Configuration Options
+
+Naming style and availability may differ slightly across platforms/languages.
+
+#### model_selection
+
+An integer index `0` or `1`. Use `0` to select a short-range model that works
+best for faces within 2 meters from the camera, and `1` for a full-range model
+best for faces within 5 meters. For the full-range option, a sparse model is
+used for its improved inference speed. Please refer to the
+[model cards](./models.md#face_detection) for details. Default to `0` if not
+specified.
+
+#### min_detection_confidence
+
+Minimum confidence value (`[0.0, 1.0]`) from the face detection model for the
+detection to be considered successful. Default to `0.5`.
+
+### Output
+
+Naming style may differ slightly across platforms/languages.
+
+#### detections
+
+Collection of detected faces, where each face is represented as a detection
+proto message that contains a bounding box and 6 key points (right eye, left
+eye, nose tip, mouth center, right ear tragion, and left ear tragion). The
+bounding box is composed of `xmin` and `width` (both normalized to `[0.0, 1.0]`
+by the image width) and `ymin` and `height` (both normalized to `[0.0, 1.0]` by
+the image height). Each key point is composed of `x` and `y`, which are
+normalized to `[0.0, 1.0]` by the image width and height respectively.
+
+### Python Solution API
+
+Please first follow general [instructions](../getting_started/python.md) to
+install MediaPipe Python package, then learn more in the companion
+[Python Colab](#resources) and the usage example below.
+
+Supported configuration options:
+
+*   [model_selection](#model_selection)
+*   [min_detection_confidence](#min_detection_confidence)
+
+```python
+import cv2
+import mediapipe as mp
+mp_face_detection = mp.solutions.face_detection
+mp_drawing = mp.solutions.drawing_utils
+
+# For static images:
+IMAGE_FILES = []
+with mp_face_detection.FaceDetection(
+    model_selection=1, min_detection_confidence=0.5) as face_detection:
+  for idx, file in enumerate(IMAGE_FILES):
+    image = cv2.imread(file)
+    # Convert the BGR image to RGB and process it with MediaPipe Face Detection.
+    results = face_detection.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+
+    # Draw face detections of each face.
+    if not results.detections:
+      continue
+    annotated_image = image.copy()
+    for detection in results.detections:
+      print('Nose tip:')
+      print(mp_face_detection.get_key_point(
+          detection, mp_face_detection.FaceKeyPoint.NOSE_TIP))
+      mp_drawing.draw_detection(annotated_image, detection)
+    cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
+
+# For webcam input:
+cap = cv2.VideoCapture(0)
+with mp_face_detection.FaceDetection(
+    model_selection=0, min_detection_confidence=0.5) as face_detection:
+  while cap.isOpened():
+    success, image = cap.read()
+    if not success:
+      print("Ignoring empty camera frame.")
+      # If loading a video, use 'break' instead of 'continue'.
+      continue
+
+    # Flip the image horizontally for a later selfie-view display, and convert
+    # the BGR image to RGB.
+    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
+    # To improve performance, optionally mark the image as not writeable to
+    # pass by reference.
+    image.flags.writeable = False
+    results = face_detection.process(image)
+
+    # Draw the face detection annotations on the image.
+    image.flags.writeable = True
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    if results.detections:
+      for detection in results.detections:
+        mp_drawing.draw_detection(image, detection)
+    cv2.imshow('MediaPipe Face Detection', image)
+    if cv2.waitKey(5) & 0xFF == 27:
+      break
+cap.release()
+```
+
+### JavaScript Solution API
+
+Please first see general [introduction](../getting_started/javascript.md) on
+MediaPipe in JavaScript, then learn more in the companion [web demo](#resources)
+and the following usage example.
+
+Supported configuration options:
+
+*   [modelSelection](#model_selection)
+*   [minDetectionConfidence](#min_detection_confidence)
+
+```html
+<!DOCTYPE html>
+<html>
+<head>
+  <meta charset="utf-8">
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/camera_utils/camera_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/control_utils/control_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/drawing_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/face_detection/face_detection.js" crossorigin="anonymous"></script>
+</head>
+
+<body>
+  <div class="container">
+    <video class="input_video"></video>
+    <canvas class="output_canvas" width="1280px" height="720px"></canvas>
+  </div>
+</body>
+</html>
+```
+
+```javascript
+<script type="module">
+const videoElement = document.getElementsByClassName('input_video')[0];
+const canvasElement = document.getElementsByClassName('output_canvas')[0];
+const canvasCtx = canvasElement.getContext('2d');
+
+function onResults(results) {
+  // Draw the overlays.
+  canvasCtx.save();
+  canvasCtx.clearRect(0, 0, canvasElement.width, canvasElement.height);
+  canvasCtx.drawImage(
+      results.image, 0, 0, canvasElement.width, canvasElement.height);
+  if (results.detections.length > 0) {
+    drawingUtils.drawRectangle(
+        canvasCtx, results.detections[0].boundingBox,
+        {color: 'blue', lineWidth: 4, fillColor: '#00000000'});
+    drawingUtils.drawLandmarks(canvasCtx, results.detections[0].landmarks, {
+      color: 'red',
+      radius: 5,
+    });
+  }
+  canvasCtx.restore();
+}
+
+const faceDetection = new FaceDetection({locateFile: (file) => {
+  return `https://cdn.jsdelivr.net/npm/@mediapipe/[email protected]/${file}`;
+}});
+faceDetection.setOptions({
+  modelSelection: 0
+  minDetectionConfidence: 0.5
+});
+faceDetection.onResults(onResults);
+
+const camera = new Camera(videoElement, {
+  onFrame: async () => {
+    await faceDetection.send({image: videoElement});
+  },
+  width: 1280,
+  height: 720
+});
+camera.start();
+</script>
+```
+
 ## Example Apps
 
 Please first see general instructions for
@@ -90,10 +267,6 @@ same configuration as the GPU pipeline, runs entirely on CPU.
     *   Target:
         [`mediapipe/examples/desktop/face_detection:face_detection_gpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/face_detection/BUILD)
 
-### Web
-
-Please refer to [these instructions](../index.md#mediapipe-on-the-web).
-
 ### Coral
 
 Please refer to
@@ -108,3 +281,5 @@ to cross-compile and run MediaPipe examples on the
     ([presentation](https://docs.google.com/presentation/d/1YCtASfnYyZtH-41QvnW5iZxELFnf0MF-pPWSLGj8yjQ/present?slide=id.g5bc8aeffdd_1_0))
     ([poster](https://drive.google.com/file/d/1u6aB6wxDY7X2TmeUUKgFydulNtXkb3pu/view))
 *   [Models and model cards](./models.md#face_detection)
+*   [Web demo](https://code.mediapipe.dev/codepen/face_detection)
+*   [Python Colab](https://mediapipe.page.link/face_detection_py_colab)

docs/solutions/face_mesh.md

@@ -69,7 +69,7 @@ and renders using a dedicated
 The
 [face landmark subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_landmark/face_landmark_front_gpu.pbtxt)
 internally uses a
-[face_detection_subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_front_gpu.pbtxt)
+[face_detection_subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range_gpu.pbtxt)
 from the
 [face detection module](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection).
 
@@ -185,8 +185,8 @@ following steps are executed in the given order:
 The geometry pipeline is implemented as a MediaPipe
 [calculator](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_geometry/geometry_pipeline_calculator.cc).
 For your convenience, the face geometry pipeline calculator is bundled together
-with the face landmark module into a unified MediaPipe
-[subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_geometry/face_geometry_front_gpu.pbtxt).
+with corresponding metadata into a unified MediaPipe
+[subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_geometry/face_geometry_from_landmarks.pbtxt).
 The face geometry format is defined as a Protocol Buffer
 [message](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_geometry/protos/face_geometry.proto).
 
@@ -264,8 +264,8 @@ magnitude of `z` uses roughly the same scale as `x`.
 ### Python Solution API
 
 Please first follow general [instructions](../getting_started/python.md) to
-install MediaPipe Python package, then learn more in the companion [Colab] and
-the following usage example.
+install MediaPipe Python package, then learn more in the companion
+[Python Colab](#resources) and the usage example below.
 
 Supported configuration options:
 
@@ -278,77 +278,94 @@ Supported configuration options:
 import cv2
 import mediapipe as mp
 mp_drawing = mp.solutions.drawing_utils
+mp_drawing_styles = mp.solutions.drawing_styles
 mp_face_mesh = mp.solutions.face_mesh
 
 # For static images:
-face_mesh = mp_face_mesh.FaceMesh(
+IMAGE_FILES = []
+drawing_spec = mp_drawing.DrawingSpec(thickness=1, circle_radius=1)
+with mp_face_mesh.FaceMesh(
     static_image_mode=True,
     max_num_faces=1,
-    min_detection_confidence=0.5)
-drawing_spec = mp_drawing.DrawingSpec(thickness=1, circle_radius=1)
-for idx, file in enumerate(file_list):
-  image = cv2.imread(file)
-  # Convert the BGR image to RGB before processing.
-  results = face_mesh.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+    min_detection_confidence=0.5) as face_mesh:
+  for idx, file in enumerate(IMAGE_FILES):
+    image = cv2.imread(file)
+    # Convert the BGR image to RGB before processing.
+    results = face_mesh.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
 
-  # Print and draw face mesh landmarks on the image.
-  if not results.multi_face_landmarks:
-    continue
-  annotated_image = image.copy()
-  for face_landmarks in results.multi_face_landmarks:
-    print('face_landmarks:', face_landmarks)
-    mp_drawing.draw_landmarks(
-        image=annotated_image,
-        landmark_list=face_landmarks,
-        connections=mp_face_mesh.FACE_CONNECTIONS,
-        landmark_drawing_spec=drawing_spec,
-        connection_drawing_spec=drawing_spec)
-  cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
-face_mesh.close()
+    # Print and draw face mesh landmarks on the image.
+    if not results.multi_face_landmarks:
+      continue
+    annotated_image = image.copy()
+    for face_landmarks in results.multi_face_landmarks:
+      print('face_landmarks:', face_landmarks)
+      mp_drawing.draw_landmarks(
+          image=annotated_image,
+          landmark_list=face_landmarks,
+          connections=mp_face_mesh.FACEMESH_TESSELATION,
+          landmark_drawing_spec=None,
+          connection_drawing_spec=mp_drawing_styles
+          .get_default_face_mesh_tesselation_style())
+      mp_drawing.draw_landmarks(
+          image=annotated_image,
+          landmark_list=face_landmarks,
+          connections=mp_face_mesh.FACEMESH_CONTOURS,
+          landmark_drawing_spec=None,
+          connection_drawing_spec=mp_drawing_styles
+          .get_default_face_mesh_contours_style())
+    cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
 
 # For webcam input:
-face_mesh = mp_face_mesh.FaceMesh(
-    min_detection_confidence=0.5, min_tracking_confidence=0.5)
 drawing_spec = mp_drawing.DrawingSpec(thickness=1, circle_radius=1)
 cap = cv2.VideoCapture(0)
-while cap.isOpened():
-  success, image = cap.read()
-  if not success:
-    print("Ignoring empty camera frame.")
-    # If loading a video, use 'break' instead of 'continue'.
-    continue
+with mp_face_mesh.FaceMesh(
+    min_detection_confidence=0.5,
+    min_tracking_confidence=0.5) as face_mesh:
+  while cap.isOpened():
+    success, image = cap.read()
+    if not success:
+      print("Ignoring empty camera frame.")
+      # If loading a video, use 'break' instead of 'continue'.
+      continue
 
-  # Flip the image horizontally for a later selfie-view display, and convert
-  # the BGR image to RGB.
-  image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
-  # To improve performance, optionally mark the image as not writeable to
-  # pass by reference.
-  image.flags.writeable = False
-  results = face_mesh.process(image)
+    # Flip the image horizontally for a later selfie-view display, and convert
+    # the BGR image to RGB.
+    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
+    # To improve performance, optionally mark the image as not writeable to
+    # pass by reference.
+    image.flags.writeable = False
+    results = face_mesh.process(image)
 
-  # Draw the face mesh annotations on the image.
-  image.flags.writeable = True
-  image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-  if results.multi_face_landmarks:
-    for face_landmarks in results.multi_face_landmarks:
-      mp_drawing.draw_landmarks(
-          image=image,
-          landmark_list=face_landmarks,
-          connections=mp_face_mesh.FACE_CONNECTIONS,
-          landmark_drawing_spec=drawing_spec,
-          connection_drawing_spec=drawing_spec)
-  cv2.imshow('MediaPipe FaceMesh', image)
-  if cv2.waitKey(5) & 0xFF == 27:
-    break
-face_mesh.close()
+    # Draw the face mesh annotations on the image.
+    image.flags.writeable = True
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    if results.multi_face_landmarks:
+      for face_landmarks in results.multi_face_landmarks:
+        mp_drawing.draw_landmarks(
+            image=image,
+            landmark_list=face_landmarks,
+            connections=mp_face_mesh.FACEMESH_TESSELATION,
+            landmark_drawing_spec=None,
+            connection_drawing_spec=mp_drawing_styles
+            .get_default_face_mesh_tesselation_style())
+        mp_drawing.draw_landmarks(
+            image=image,
+            landmark_list=face_landmarks,
+            connections=mp_face_mesh.FACEMESH_CONTOURS,
+            landmark_drawing_spec=None,
+            connection_drawing_spec=mp_drawing_styles
+            .get_default_face_mesh_contours_style())
+    cv2.imshow('MediaPipe FaceMesh', image)
+    if cv2.waitKey(5) & 0xFF == 27:
+      break
 cap.release()
 ```
 
 ### JavaScript Solution API
 
 Please first see general [introduction](../getting_started/javascript.md) on
-MediaPipe in JavaScript, then learn more in the companion [web demo] and the
-following usage example.
+MediaPipe in JavaScript, then learn more in the companion [web demo](#resources)
+and the following usage example.
 
 Supported configuration options:
 
@@ -423,6 +440,200 @@ camera.start();
 </script>
 ```
 
+### Android Solution API
+
+Please first follow general
+[instructions](../getting_started/android_solutions.md#integrate-mediapipe-android-solutions-api)
+to add MediaPipe Gradle dependencies, then try the FaceMash solution API in the
+companion
+[example Android Studio project](https://github.com/google/mediapipe/tree/master/mediapipe/examples/android/solutions/facemesh)
+following
+[these instructions](../getting_started/android_solutions.md#build-solution-example-apps-in-android-studio)
+and learn more in the usage example below.
+
+Supported configuration options:
+
+*   [staticImageMode](#static_image_mode)
+*   [maxNumFaces](#max_num_faces)
+*   runOnGpu: Run the pipeline and the model inference on GPU or CPU.
+
+#### Camera Input
+
+```java
+// For camera input and result rendering with OpenGL.
+FaceMeshOptions faceMeshOptions =
+    FaceMeshOptions.builder()
+        .setMode(FaceMeshOptions.STREAMING_MODE)  // API soon to become
+        .setMaxNumFaces(1)                        // setStaticImageMode(false)
+        .setRunOnGpu(true).build();
+FaceMesh facemesh = new FaceMesh(this, faceMeshOptions);
+facemesh.setErrorListener(
+    (message, e) -> Log.e(TAG, "MediaPipe FaceMesh error:" + message));
+
+// Initializes a new CameraInput instance and connects it to MediaPipe FaceMesh.
+CameraInput cameraInput = new CameraInput(this);
+cameraInput.setNewFrameListener(
+    textureFrame -> facemesh.send(textureFrame));
+
+// Initializes a new GlSurfaceView with a ResultGlRenderer<FaceMeshResult> instance
+// that provides the interfaces to run user-defined OpenGL rendering code.
+// See mediapipe/examples/android/solutions/facemesh/src/main/java/com/google/mediapipe/examples/facemesh/FaceMeshResultGlRenderer.java
+// as an example.
+SolutionGlSurfaceView<FaceMeshResult> glSurfaceView =
+    new SolutionGlSurfaceView<>(
+        this, facemesh.getGlContext(), facemesh.getGlMajorVersion());
+glSurfaceView.setSolutionResultRenderer(new FaceMeshResultGlRenderer());
+glSurfaceView.setRenderInputImage(true);
+
+facemesh.setResultListener(
+    faceMeshResult -> {
+      NormalizedLandmark noseLandmark =
+          result.multiFaceLandmarks().get(0).getLandmarkList().get(1);
+      Log.i(
+          TAG,
+          String.format(
+              "MediaPipe FaceMesh nose normalized coordinates (value range: [0, 1]): x=%f, y=%f",
+              noseLandmark.getX(), noseLandmark.getY()));
+      // Request GL rendering.
+      glSurfaceView.setRenderData(faceMeshResult);
+      glSurfaceView.requestRender();
+    });
+
+// The runnable to start camera after the GLSurfaceView is attached.
+glSurfaceView.post(
+    () ->
+        cameraInput.start(
+            this,
+            facemesh.getGlContext(),
+            CameraInput.CameraFacing.FRONT,
+            glSurfaceView.getWidth(),
+            glSurfaceView.getHeight()));
+```
+
+#### Image Input
+
+```java
+// For reading images from gallery and drawing the output in an ImageView.
+FaceMeshOptions faceMeshOptions =
+    FaceMeshOptions.builder()
+        .setMode(FaceMeshOptions.STATIC_IMAGE_MODE)  // API soon to become
+        .setMaxNumFaces(1)                           // setStaticImageMode(true)
+        .setRunOnGpu(true).build();
+FaceMesh facemesh = new FaceMesh(this, faceMeshOptions);
+
+// Connects MediaPipe FaceMesh to the user-defined ImageView instance that allows
+// users to have the custom drawing of the output landmarks on it.
+// See mediapipe/examples/android/solutions/facemesh/src/main/java/com/google/mediapipe/examples/facemesh/FaceMeshResultImageView.java
+// as an example.
+FaceMeshResultImageView imageView = new FaceMeshResultImageView(this);
+facemesh.setResultListener(
+    faceMeshResult -> {
+      int width = faceMeshResult.inputBitmap().getWidth();
+      int height = faceMeshResult.inputBitmap().getHeight();
+      NormalizedLandmark noseLandmark =
+          result.multiFaceLandmarks().get(0).getLandmarkList().get(1);
+      Log.i(
+          TAG,
+          String.format(
+              "MediaPipe FaceMesh nose coordinates (pixel values): x=%f, y=%f",
+              noseLandmark.getX() * width, noseLandmark.getY() * height));
+      // Request canvas drawing.
+      imageView.setFaceMeshResult(faceMeshResult);
+      runOnUiThread(() -> imageView.update());
+    });
+facemesh.setErrorListener(
+    (message, e) -> Log.e(TAG, "MediaPipe FaceMesh error:" + message));
+
+// ActivityResultLauncher to get an image from the gallery as Bitmap.
+ActivityResultLauncher<Intent> imageGetter =
+    registerForActivityResult(
+        new ActivityResultContracts.StartActivityForResult(),
+        result -> {
+          Intent resultIntent = result.getData();
+          if (resultIntent != null && result.getResultCode() == RESULT_OK) {
+            Bitmap bitmap = null;
+            try {
+              bitmap =
+                  MediaStore.Images.Media.getBitmap(
+                      this.getContentResolver(), resultIntent.getData());
+            } catch (IOException e) {
+              Log.e(TAG, "Bitmap reading error:" + e);
+            }
+            if (bitmap != null) {
+              facemesh.send(bitmap);
+            }
+          }
+        });
+Intent gallery = new Intent(
+    Intent.ACTION_PICK, MediaStore.Images.Media.INTERNAL_CONTENT_URI);
+imageGetter.launch(gallery);
+```
+
+#### Video Input
+
+```java
+// For video input and result rendering with OpenGL.
+FaceMeshOptions faceMeshOptions =
+    FaceMeshOptions.builder()
+        .setMode(FaceMeshOptions.STREAMING_MODE)  // API soon to become
+        .setMaxNumFaces(1)                        // setStaticImageMode(false)
+        .setRunOnGpu(true).build();
+FaceMesh facemesh = new FaceMesh(this, faceMeshOptions);
+facemesh.setErrorListener(
+    (message, e) -> Log.e(TAG, "MediaPipe FaceMesh error:" + message));
+
+// Initializes a new VideoInput instance and connects it to MediaPipe FaceMesh.
+VideoInput videoInput = new VideoInput(this);
+videoInput.setNewFrameListener(
+    textureFrame -> facemesh.send(textureFrame));
+
+// Initializes a new GlSurfaceView with a ResultGlRenderer<FaceMeshResult> instance
+// that provides the interfaces to run user-defined OpenGL rendering code.
+// See mediapipe/examples/android/solutions/facemesh/src/main/java/com/google/mediapipe/examples/facemesh/FaceMeshResultGlRenderer.java
+// as an example.
+SolutionGlSurfaceView<FaceMeshResult> glSurfaceView =
+    new SolutionGlSurfaceView<>(
+        this, facemesh.getGlContext(), facemesh.getGlMajorVersion());
+glSurfaceView.setSolutionResultRenderer(new FaceMeshResultGlRenderer());
+glSurfaceView.setRenderInputImage(true);
+
+facemesh.setResultListener(
+    faceMeshResult -> {
+      NormalizedLandmark noseLandmark =
+          result.multiFaceLandmarks().get(0).getLandmarkList().get(1);
+      Log.i(
+          TAG,
+          String.format(
+              "MediaPipe FaceMesh nose normalized coordinates (value range: [0, 1]): x=%f, y=%f",
+              noseLandmark.getX(), noseLandmark.getY()));
+      // Request GL rendering.
+      glSurfaceView.setRenderData(faceMeshResult);
+      glSurfaceView.requestRender();
+    });
+
+ActivityResultLauncher<Intent> videoGetter =
+    registerForActivityResult(
+        new ActivityResultContracts.StartActivityForResult(),
+        result -> {
+          Intent resultIntent = result.getData();
+          if (resultIntent != null) {
+            if (result.getResultCode() == RESULT_OK) {
+              glSurfaceView.post(
+                  () ->
+                      videoInput.start(
+                          this,
+                          resultIntent.getData(),
+                          facemesh.getGlContext(),
+                          glSurfaceView.getWidth(),
+                          glSurfaceView.getHeight()));
+            }
+          }
+        });
+Intent gallery =
+    new Intent(Intent.ACTION_PICK, MediaStore.Video.Media.INTERNAL_CONTENT_URI);
+videoGetter.launch(gallery);
+```
+
 ## Example Apps
 
 Please first see general instructions for
@@ -503,7 +714,5 @@ only works for a single face. For visual reference, please refer to *Fig. 4*.
     [OBJ](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_geometry/data/canonical_face_model.obj),
     [UV visualization](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_geometry/data/canonical_face_model_uv_visualization.png)
 *   [Models and model cards](./models.md#face_mesh)
-
-[Colab]:https://mediapipe.page.link/face_mesh_py_colab
-
-[web demo]:https://code.mediapipe.dev/codepen/face_mesh
+*   [Web demo](https://code.mediapipe.dev/codepen/face_mesh)
+*   [Python Colab](https://mediapipe.page.link/face_mesh_py_colab)

docs/solutions/hair_segmentation.md

@@ -2,7 +2,7 @@
 layout: default
 title: Hair Segmentation
 parent: Solutions
-nav_order: 7
+nav_order: 8
 ---
 
 # MediaPipe Hair Segmentation
@@ -51,7 +51,14 @@ to visualize its associated subgraphs, please see
 
 ### Web
 
-Please refer to [these instructions](../index.md#mediapipe-on-the-web).
+Use [this link](https://viz.mediapipe.dev/demo/hair_segmentation) to load a demo
+in the MediaPipe Visualizer, and over there click the "Runner" icon in the top
+bar like shown below. The demos use your webcam video as input, which is
+processed all locally in real-time and never leaves your device. Please see
+[MediaPipe on the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html)
+in Google Developers Blog for details.
+
+![visualizer_runner](../images/visualizer_runner.png)
 
 ## Resources
 

docs/solutions/hands.md

@@ -91,13 +91,14 @@ To detect initial hand locations, we designed a
 mobile real-time uses in a manner similar to the face detection model in
 [MediaPipe Face Mesh](./face_mesh.md). Detecting hands is a decidedly complex
 task: our
-[model](https://github.com/google/mediapipe/tree/master/mediapipe/models/palm_detection.tflite) has
-to work across a variety of hand sizes with a large scale span (~20x) relative
-to the image frame and be able to detect occluded and self-occluded hands.
-Whereas faces have high contrast patterns, e.g., in the eye and mouth region,
-the lack of such features in hands makes it comparatively difficult to detect
-them reliably from their visual features alone. Instead, providing additional
-context, like arm, body, or person features, aids accurate hand localization.
+[model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/palm_detection/palm_detection.tflite)
+has to work across a variety of hand sizes with a large scale span (~20x)
+relative to the image frame and be able to detect occluded and self-occluded
+hands. Whereas faces have high contrast patterns, e.g., in the eye and mouth
+region, the lack of such features in hands makes it comparatively difficult to
+detect them reliably from their visual features alone. Instead, providing
+additional context, like arm, body, or person features, aids accurate hand
+localization.
 
 Our method addresses the above challenges using different strategies. First, we
 train a palm detector instead of a hand detector, since estimating bounding
@@ -119,7 +120,7 @@ just 86.22%.
 ### Hand Landmark Model
 
 After the palm detection over the whole image our subsequent hand landmark
-[model](https://github.com/google/mediapipe/tree/master/mediapipe/models/hand_landmark.tflite)
+[model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/hand_landmark/hand_landmark.tflite)
 performs precise keypoint localization of 21 3D hand-knuckle coordinates inside
 the detected hand regions via regression, that is direct coordinate prediction.
 The model learns a consistent internal hand pose representation and is robust
@@ -136,11 +137,9 @@ to the corresponding 3D coordinates.
 :--------------------------------------------------------: |
 *Fig 2. 21 hand landmarks.*                                |
 
-| ![hand_crops.png](../images/mobile/hand_crops.png)                          |
-| :-------------------------------------------------------------------------: |
-| *Fig 3. Top: Aligned hand crops passed to the tracking network with ground  |
-: truth annotation. Bottom\: Rendered synthetic hand images with ground truth :
-: annotation.*                                                                :
+![hand_crops.png](../images/mobile/hand_crops.png)                          |
+:-------------------------------------------------------------------------: |
+*Fig 3. Top: Aligned hand crops passed to the tracking network with ground truth annotation. Bottom: Rendered synthetic hand images with ground truth annotation.* |
 
 ## Solution APIs
 
@@ -206,8 +205,8 @@ is not the case, please swap the handedness output in the application.
 ### Python Solution API
 
 Please first follow general [instructions](../getting_started/python.md) to
-install MediaPipe Python package, then learn more in the companion [Colab] and
-the following usage example.
+install MediaPipe Python package, then learn more in the companion
+[Python Colab](#resources) and the usage example below.
 
 Supported configuration options:
 
@@ -220,77 +219,86 @@ Supported configuration options:
 import cv2
 import mediapipe as mp
 mp_drawing = mp.solutions.drawing_utils
+mp_drawing_styles = mp.solutions.drawing_styles
 mp_hands = mp.solutions.hands
 
 # For static images:
-hands = mp_hands.Hands(
+IMAGE_FILES = []
+with mp_hands.Hands(
     static_image_mode=True,
     max_num_hands=2,
-    min_detection_confidence=0.5)
-for idx, file in enumerate(file_list):
-  # Read an image, flip it around y-axis for correct handedness output (see
-  # above).
-  image = cv2.flip(cv2.imread(file), 1)
-  # Convert the BGR image to RGB before processing.
-  results = hands.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+    min_detection_confidence=0.5) as hands:
+  for idx, file in enumerate(IMAGE_FILES):
+    # Read an image, flip it around y-axis for correct handedness output (see
+    # above).
+    image = cv2.flip(cv2.imread(file), 1)
+    # Convert the BGR image to RGB before processing.
+    results = hands.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
 
-  # Print handedness and draw hand landmarks on the image.
-  print('Handedness:', results.multi_handedness)
-  if not results.multi_hand_landmarks:
-    continue
-  image_hight, image_width, _ = image.shape
-  annotated_image = image.copy()
-  for hand_landmarks in results.multi_hand_landmarks:
-    print('hand_landmarks:', hand_landmarks)
-    print(
-        f'Index finger tip coordinates: (',
-        f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].x * image_width}, '
-        f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].y * image_hight})'
-    )
-    mp_drawing.draw_landmarks(
-        annotated_image, hand_landmarks, mp_hands.HAND_CONNECTIONS)
-  cv2.imwrite(
-      '/tmp/annotated_image' + str(idx) + '.png', cv2.flip(annotated_image, 1))
-hands.close()
+    # Print handedness and draw hand landmarks on the image.
+    print('Handedness:', results.multi_handedness)
+    if not results.multi_hand_landmarks:
+      continue
+    image_height, image_width, _ = image.shape
+    annotated_image = image.copy()
+    for hand_landmarks in results.multi_hand_landmarks:
+      print('hand_landmarks:', hand_landmarks)
+      print(
+          f'Index finger tip coordinates: (',
+          f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].x * image_width}, '
+          f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].y * image_height})'
+      )
+      mp_drawing.draw_landmarks(
+          annotated_image,
+          hand_landmarks,
+          mp_hands.HAND_CONNECTIONS,
+          mp_drawing_styles.get_default_hand_landmarks_style(),
+          mp_drawing_styles.get_default_hand_connections_style())
+    cv2.imwrite(
+        '/tmp/annotated_image' + str(idx) + '.png', cv2.flip(annotated_image, 1))
 
 # For webcam input:
-hands = mp_hands.Hands(
-    min_detection_confidence=0.5, min_tracking_confidence=0.5)
 cap = cv2.VideoCapture(0)
-while cap.isOpened():
-  success, image = cap.read()
-  if not success:
-    print("Ignoring empty camera frame.")
-    # If loading a video, use 'break' instead of 'continue'.
-    continue
+with mp_hands.Hands(
+    min_detection_confidence=0.5,
+    min_tracking_confidence=0.5) as hands:
+  while cap.isOpened():
+    success, image = cap.read()
+    if not success:
+      print("Ignoring empty camera frame.")
+      # If loading a video, use 'break' instead of 'continue'.
+      continue
 
-  # Flip the image horizontally for a later selfie-view display, and convert
-  # the BGR image to RGB.
-  image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
-  # To improve performance, optionally mark the image as not writeable to
-  # pass by reference.
-  image.flags.writeable = False
-  results = hands.process(image)
+    # Flip the image horizontally for a later selfie-view display, and convert
+    # the BGR image to RGB.
+    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
+    # To improve performance, optionally mark the image as not writeable to
+    # pass by reference.
+    image.flags.writeable = False
+    results = hands.process(image)
 
-  # Draw the hand annotations on the image.
-  image.flags.writeable = True
-  image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-  if results.multi_hand_landmarks:
-    for hand_landmarks in results.multi_hand_landmarks:
-      mp_drawing.draw_landmarks(
-          image, hand_landmarks, mp_hands.HAND_CONNECTIONS)
-  cv2.imshow('MediaPipe Hands', image)
-  if cv2.waitKey(5) & 0xFF == 27:
-    break
-hands.close()
+    # Draw the hand annotations on the image.
+    image.flags.writeable = True
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    if results.multi_hand_landmarks:
+      for hand_landmarks in results.multi_hand_landmarks:
+        mp_drawing.draw_landmarks(
+            image,
+            hand_landmarks,
+            mp_hands.HAND_CONNECTIONS,
+            mp_drawing_styles.get_default_hand_landmarks_style(),
+            mp_drawing_styles.get_default_hand_connections_style())
+    cv2.imshow('MediaPipe Hands', image)
+    if cv2.waitKey(5) & 0xFF == 27:
+      break
 cap.release()
 ```
 
 ### JavaScript Solution API
 
 Please first see general [introduction](../getting_started/javascript.md) on
-MediaPipe in JavaScript, then learn more in the companion [web demo] and a
-[fun application], and the following usage example.
+MediaPipe in JavaScript, then learn more in the companion [web demo](#resources)
+and a [fun application], and the following usage example.
 
 Supported configuration options:
 
@@ -360,6 +368,200 @@ camera.start();
 </script>
 ```
 
+### Android Solution API
+
+Please first follow general
+[instructions](../getting_started/android_solutions.md#integrate-mediapipe-android-solutions-api)
+to add MediaPipe Gradle dependencies, then try the Hands solution API in the
+companion
+[example Android Studio project](https://github.com/google/mediapipe/tree/master/mediapipe/examples/android/solutions/hands)
+following
+[these instructions](../getting_started/android_solutions.md#build-solution-example-apps-in-android-studio)
+and learn more in usage example below.
+
+Supported configuration options:
+
+*   [staticImageMode](#static_image_mode)
+*   [maxNumHands](#max_num_hands)
+*   runOnGpu: Run the pipeline and the model inference on GPU or CPU.
+
+#### Camera Input
+
+```java
+// For camera input and result rendering with OpenGL.
+HandsOptions handsOptions =
+    HandsOptions.builder()
+        .setMode(HandsOptions.STREAMING_MODE)  // API soon to become
+        .setMaxNumHands(1)                     // setStaticImageMode(false)
+        .setRunOnGpu(true).build();
+Hands hands = new Hands(this, handsOptions);
+hands.setErrorListener(
+    (message, e) -> Log.e(TAG, "MediaPipe Hands error:" + message));
+
+// Initializes a new CameraInput instance and connects it to MediaPipe Hands.
+CameraInput cameraInput = new CameraInput(this);
+cameraInput.setNewFrameListener(
+    textureFrame -> hands.send(textureFrame));
+
+// Initializes a new GlSurfaceView with a ResultGlRenderer<HandsResult> instance
+// that provides the interfaces to run user-defined OpenGL rendering code.
+// See mediapipe/examples/android/solutions/hands/src/main/java/com/google/mediapipe/examples/hands/HandsResultGlRenderer.java
+// as an example.
+SolutionGlSurfaceView<HandsResult> glSurfaceView =
+    new SolutionGlSurfaceView<>(
+        this, hands.getGlContext(), hands.getGlMajorVersion());
+glSurfaceView.setSolutionResultRenderer(new HandsResultGlRenderer());
+glSurfaceView.setRenderInputImage(true);
+
+hands.setResultListener(
+    handsResult -> {
+      NormalizedLandmark wristLandmark = Hands.getHandLandmark(
+          handsResult, 0, HandLandmark.WRIST);
+      Log.i(
+          TAG,
+          String.format(
+              "MediaPipe Hand wrist normalized coordinates (value range: [0, 1]): x=%f, y=%f",
+              wristLandmark.getX(), wristLandmark.getY()));
+      // Request GL rendering.
+      glSurfaceView.setRenderData(handsResult);
+      glSurfaceView.requestRender();
+    });
+
+// The runnable to start camera after the GLSurfaceView is attached.
+glSurfaceView.post(
+    () ->
+        cameraInput.start(
+            this,
+            hands.getGlContext(),
+            CameraInput.CameraFacing.FRONT,
+            glSurfaceView.getWidth(),
+            glSurfaceView.getHeight()));
+```
+
+#### Image Input
+
+```java
+// For reading images from gallery and drawing the output in an ImageView.
+HandsOptions handsOptions =
+    HandsOptions.builder()
+        .setMode(HandsOptions.STATIC_IMAGE_MODE)  // API soon to become
+        .setMaxNumHands(1)                        // setStaticImageMode(true)
+        .setRunOnGpu(true).build();
+Hands hands = new Hands(this, handsOptions);
+
+// Connects MediaPipe Hands to the user-defined ImageView instance that allows
+// users to have the custom drawing of the output landmarks on it.
+// See mediapipe/examples/android/solutions/hands/src/main/java/com/google/mediapipe/examples/hands/HandsResultImageView.java
+// as an example.
+HandsResultImageView imageView = new HandsResultImageView(this);
+hands.setResultListener(
+    handsResult -> {
+      int width = handsResult.inputBitmap().getWidth();
+      int height = handsResult.inputBitmap().getHeight();
+      NormalizedLandmark wristLandmark = Hands.getHandLandmark(
+          handsResult, 0, HandLandmark.WRIST);
+      Log.i(
+          TAG,
+          String.format(
+              "MediaPipe Hand wrist coordinates (pixel values): x=%f, y=%f",
+              wristLandmark.getX() * width, wristLandmark.getY() * height));
+      // Request canvas drawing.
+      imageView.setHandsResult(handsResult);
+      runOnUiThread(() -> imageView.update());
+    });
+hands.setErrorListener(
+    (message, e) -> Log.e(TAG, "MediaPipe Hands error:" + message));
+
+// ActivityResultLauncher to get an image from the gallery as Bitmap.
+ActivityResultLauncher<Intent> imageGetter =
+    registerForActivityResult(
+        new ActivityResultContracts.StartActivityForResult(),
+        result -> {
+          Intent resultIntent = result.getData();
+          if (resultIntent != null && result.getResultCode() == RESULT_OK) {
+            Bitmap bitmap = null;
+            try {
+              bitmap =
+                  MediaStore.Images.Media.getBitmap(
+                      this.getContentResolver(), resultIntent.getData());
+            } catch (IOException e) {
+              Log.e(TAG, "Bitmap reading error:" + e);
+            }
+            if (bitmap != null) {
+              hands.send(bitmap);
+            }
+          }
+        });
+Intent gallery = new Intent(
+    Intent.ACTION_PICK, MediaStore.Images.Media.INTERNAL_CONTENT_URI);
+imageGetter.launch(gallery);
+```
+
+#### Video Input
+
+```java
+// For video input and result rendering with OpenGL.
+HandsOptions handsOptions =
+    HandsOptions.builder()
+        .setMode(HandsOptions.STREAMING_MODE)  // API soon to become
+        .setMaxNumHands(1)                     // setStaticImageMode(false)
+        .setRunOnGpu(true).build();
+Hands hands = new Hands(this, handsOptions);
+hands.setErrorListener(
+    (message, e) -> Log.e(TAG, "MediaPipe Hands error:" + message));
+
+// Initializes a new VideoInput instance and connects it to MediaPipe Hands.
+VideoInput videoInput = new VideoInput(this);
+videoInput.setNewFrameListener(
+    textureFrame -> hands.send(textureFrame));
+
+// Initializes a new GlSurfaceView with a ResultGlRenderer<HandsResult> instance
+// that provides the interfaces to run user-defined OpenGL rendering code.
+// See mediapipe/examples/android/solutions/hands/src/main/java/com/google/mediapipe/examples/hands/HandsResultGlRenderer.java
+// as an example.
+SolutionGlSurfaceView<HandsResult> glSurfaceView =
+    new SolutionGlSurfaceView<>(
+        this, hands.getGlContext(), hands.getGlMajorVersion());
+glSurfaceView.setSolutionResultRenderer(new HandsResultGlRenderer());
+glSurfaceView.setRenderInputImage(true);
+
+hands.setResultListener(
+    handsResult -> {
+      NormalizedLandmark wristLandmark = Hands.getHandLandmark(
+          handsResult, 0, HandLandmark.WRIST);
+      Log.i(
+          TAG,
+          String.format(
+              "MediaPipe Hand wrist normalized coordinates (value range: [0, 1]): x=%f, y=%f",
+              wristLandmark.getX(), wristLandmark.getY()));
+      // Request GL rendering.
+      glSurfaceView.setRenderData(handsResult);
+      glSurfaceView.requestRender();
+    });
+
+ActivityResultLauncher<Intent> videoGetter =
+    registerForActivityResult(
+        new ActivityResultContracts.StartActivityForResult(),
+        result -> {
+          Intent resultIntent = result.getData();
+          if (resultIntent != null) {
+            if (result.getResultCode() == RESULT_OK) {
+              glSurfaceView.post(
+                  () ->
+                      videoInput.start(
+                          this,
+                          resultIntent.getData(),
+                          hands.getGlContext(),
+                          glSurfaceView.getWidth(),
+                          glSurfaceView.getHeight()));
+            }
+          }
+        });
+Intent gallery =
+    new Intent(Intent.ACTION_PICK, MediaStore.Video.Media.INTERNAL_CONTENT_URI);
+videoGetter.launch(gallery);
+```
+
 ## Example Apps
 
 Please first see general instructions for
@@ -425,8 +627,6 @@ it, in the graph file modify the option of `ConstantSidePacketCalculator`.
     [MediaPipe Hands: On-device Real-time Hand Tracking](https://arxiv.org/abs/2006.10214)
     ([presentation](https://www.youtube.com/watch?v=I-UOrvxxXEk))
 *   [Models and model cards](./models.md#hands)
-
-[Colab]:https://mediapipe.page.link/hands_py_colab
-
-[web demo]:https://code.mediapipe.dev/codepen/hands
-[fun application]:https://code.mediapipe.dev/codepen/defrost
+*   [Web demo](https://code.mediapipe.dev/codepen/hands)
+*   [Fun application](https://code.mediapipe.dev/codepen/defrost)
+*   [Python Colab](https://mediapipe.page.link/hands_py_colab)

docs/solutions/holistic.md

@@ -135,12 +135,11 @@ another detection until it loses track, on reducing computation and latency. If
 set to `true`, person detection runs every input image, ideal for processing a
 batch of static, possibly unrelated, images. Default to `false`.
 
-#### upper_body_only
+#### model_complexity
 
-If set to `true`, the solution outputs only the 25 upper-body pose landmarks
-(535 in total) instead of the full set of 33 pose landmarks (543 in total). Note
-that upper-body-only prediction may be more accurate for use cases where the
-lower-body parts are mostly out of view. Default to `false`.
+Complexity of the pose landmark model: `0`, `1` or `2`. Landmark accuracy as
+well as inference latency generally go up with the model complexity. Default to
+`1`.
 
 #### smooth_landmarks
 
@@ -177,6 +176,16 @@ A list of pose landmarks. Each landmark consists of the following:
 *   `visibility`: A value in `[0.0, 1.0]` indicating the likelihood of the
     landmark being visible (present and not occluded) in the image.
 
+#### pose_world_landmarks
+
+Another list of pose landmarks in world coordinates. Each landmark consists of
+the following:
+
+*   `x`, `y` and `z`: Real-world 3D coordinates in meters with the origin at the
+    center between hips.
+*   `visibility`: Identical to that defined in the corresponding
+    [pose_landmarks](#pose_landmarks).
+
 #### face_landmarks
 
 A list of 468 face landmarks. Each landmark consists of `x`, `y` and `z`. `x`
@@ -201,13 +210,13 @@ A list of 21 hand landmarks on the right hand, in the same representation as
 ### Python Solution API
 
 Please first follow general [instructions](../getting_started/python.md) to
-install MediaPipe Python package, then learn more in the companion [Colab] and
-the following usage example.
+install MediaPipe Python package, then learn more in the companion
+[Python Colab](#resources) and the usage example below.
 
 Supported configuration options:
 
 *   [static_image_mode](#static_image_mode)
-*   [upper_body_only](#upper_body_only)
+*   [model_complexity](#model_complexity)
 *   [smooth_landmarks](#smooth_landmarks)
 *   [min_detection_confidence](#min_detection_confidence)
 *   [min_tracking_confidence](#min_tracking_confidence)
@@ -216,81 +225,97 @@ Supported configuration options:
 import cv2
 import mediapipe as mp
 mp_drawing = mp.solutions.drawing_utils
+mp_drawing_styles = mp.solutions.drawing_styles
 mp_holistic = mp.solutions.holistic
 
 # For static images:
-holistic = mp_holistic.Holistic(static_image_mode=True)
-for idx, file in enumerate(file_list):
-  image = cv2.imread(file)
-  image_hight, image_width, _ = image.shape
-  # Convert the BGR image to RGB before processing.
-  results = holistic.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+IMAGE_FILES = []
+with mp_holistic.Holistic(
+    static_image_mode=True,
+    model_complexity=2) as holistic:
+  for idx, file in enumerate(IMAGE_FILES):
+    image = cv2.imread(file)
+    image_height, image_width, _ = image.shape
+    # Convert the BGR image to RGB before processing.
+    results = holistic.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
 
-  if results.pose_landmarks:
-    print(
-        f'Nose coordinates: ('
-        f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].x * image_width}, '
-        f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].y * image_hight})'
-    )
-  # Draw pose, left and right hands, and face landmarks on the image.
-  annotated_image = image.copy()
-  mp_drawing.draw_landmarks(
-      annotated_image, results.face_landmarks, mp_holistic.FACE_CONNECTIONS)
-  mp_drawing.draw_landmarks(
-      annotated_image, results.left_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
-  mp_drawing.draw_landmarks(
-      annotated_image, results.right_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
-  mp_drawing.draw_landmarks(
-      annotated_image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS)
-  cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
-holistic.close()
+    if results.pose_landmarks:
+      print(
+          f'Nose coordinates: ('
+          f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].x * image_width}, '
+          f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].y * image_height})'
+      )
+    # Draw pose, left and right hands, and face landmarks on the image.
+    annotated_image = image.copy()
+    mp_drawing.draw_landmarks(
+        annotated_image,
+        results.face_landmarks,
+        mp_holistic.FACEMESH_TESSELATION,
+        landmark_drawing_spec=None,
+        connection_drawing_spec=mp_drawing_styles
+        .get_default_face_mesh_tesselation_style())
+    mp_drawing.draw_landmarks(
+        annotated_image,
+        results.pose_landmarks,
+        mp_holistic.POSE_CONNECTIONS,
+        landmark_drawing_spec=mp_drawing_styles.
+        get_default_pose_landmarks_style())
+    cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
+    # Plot pose world landmarks.
+    mp_drawing.plot_landmarks(
+        results.pose_world_landmarks, mp_holistic.POSE_CONNECTIONS)
 
 # For webcam input:
-holistic = mp_holistic.Holistic(
-    min_detection_confidence=0.5, min_tracking_confidence=0.5)
 cap = cv2.VideoCapture(0)
-while cap.isOpened():
-  success, image = cap.read()
-  if not success:
-    print("Ignoring empty camera frame.")
-    # If loading a video, use 'break' instead of 'continue'.
-    continue
+with mp_holistic.Holistic(
+    min_detection_confidence=0.5,
+    min_tracking_confidence=0.5) as holistic:
+  while cap.isOpened():
+    success, image = cap.read()
+    if not success:
+      print("Ignoring empty camera frame.")
+      # If loading a video, use 'break' instead of 'continue'.
+      continue
 
-  # Flip the image horizontally for a later selfie-view display, and convert
-  # the BGR image to RGB.
-  image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
-  # To improve performance, optionally mark the image as not writeable to
-  # pass by reference.
-  image.flags.writeable = False
-  results = holistic.process(image)
+    # Flip the image horizontally for a later selfie-view display, and convert
+    # the BGR image to RGB.
+    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
+    # To improve performance, optionally mark the image as not writeable to
+    # pass by reference.
+    image.flags.writeable = False
+    results = holistic.process(image)
 
-  # Draw landmark annotation on the image.
-  image.flags.writeable = True
-  image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-  mp_drawing.draw_landmarks(
-      image, results.face_landmarks, mp_holistic.FACE_CONNECTIONS)
-  mp_drawing.draw_landmarks(
-      image, results.left_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
-  mp_drawing.draw_landmarks(
-      image, results.right_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
-  mp_drawing.draw_landmarks(
-      image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS)
-  cv2.imshow('MediaPipe Holistic', image)
-  if cv2.waitKey(5) & 0xFF == 27:
-    break
-holistic.close()
+    # Draw landmark annotation on the image.
+    image.flags.writeable = True
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    mp_drawing.draw_landmarks(
+        image,
+        results.face_landmarks,
+        mp_holistic.FACEMESH_CONTOURS,
+        landmark_drawing_spec=None,
+        connection_drawing_spec=mp_drawing_styles
+        .get_default_face_mesh_contours_style())
+    mp_drawing.draw_landmarks(
+        image,
+        results.pose_landmarks,
+        mp_holistic.POSE_CONNECTIONS,
+        landmark_drawing_spec=mp_drawing_styles
+        .get_default_pose_landmarks_style())
+    cv2.imshow('MediaPipe Holistic', image)
+    if cv2.waitKey(5) & 0xFF == 27:
+      break
 cap.release()
 ```
 
 ### JavaScript Solution API
 
 Please first see general [introduction](../getting_started/javascript.md) on
-MediaPipe in JavaScript, then learn more in the companion [web demo] and the
-following usage example.
+MediaPipe in JavaScript, then learn more in the companion [web demo](#resources)
+and the following usage example.
 
 Supported configuration options:
 
-*   [upperBodyOnly](#upper_body_only)
+*   [modelComplexity](#model_complexity)
 *   [smoothLandmarks](#smooth_landmarks)
 *   [minDetectionConfidence](#min_detection_confidence)
 *   [minTrackingConfidence](#min_tracking_confidence)
@@ -347,7 +372,7 @@ const holistic = new Holistic({locateFile: (file) => {
   return `https://cdn.jsdelivr.net/npm/@mediapipe/holistic/${file}`;
 }});
 holistic.setOptions({
-  upperBodyOnly: false,
+  modelComplexity: 1,
   smoothLandmarks: true,
   minDetectionConfidence: 0.5,
   minTrackingConfidence: 0.5
@@ -405,9 +430,7 @@ on how to build MediaPipe examples.
 ## Resources
 
 *   Google AI Blog:
-    [MediaPipe Holistic - Simultaneous Face, Hand and Pose Prediction on Device](https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html)
+    [MediaPipe Holistic - Simultaneous Face, Hand and Pose Prediction, on Device](https://ai.googleblog.com/2020/12/mediapipe-holistic-simultaneous-face.html)
 *   [Models and model cards](./models.md#holistic)
-
-[Colab]:https://mediapipe.page.link/holistic_py_colab
-
-[web demo]:https://code.mediapipe.dev/codepen/holistic
+*   [Web demo](https://code.mediapipe.dev/codepen/holistic)
+*   [Python Colab](https://mediapipe.page.link/holistic_py_colab)

docs/solutions/instant_motion_tracking.md

@@ -2,7 +2,7 @@
 layout: default
 title: Instant Motion Tracking
 parent: Solutions
-nav_order: 10
+nav_order: 11
 ---
 
 # MediaPipe Instant Motion Tracking
@@ -117,6 +117,25 @@ Please first see general instructions for
 * Android target (or download prebuilt [ARM64 APK](https://drive.google.com/file/d/1KnaBBoKpCHR73nOBJ4fL_YdWVTAcwe6L/view?usp=sharing)):
 [`mediapipe/examples/android/src/java/com/google/mediapipe/apps/instantmotiontracking:instantmotiontracking`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/instantmotiontracking/BUILD)
 
+* Assets rendered by the [GlAnimationOverlayCalculator](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/object_detection_3d/calculators/gl_animation_overlay_calculator.cc) must be preprocessed into an OpenGL-ready custom .uuu format. This can be done
+for user assets as follows:
+> First run
+>
+> ```shell
+> ./mediapipe/graphs/object_detection_3d/obj_parser/obj_cleanup.sh [INPUT_DIR] [INTERMEDIATE_OUTPUT_DIR]
+> ```
+> and then run
+>
+> ```build
+> bazel run -c opt mediapipe/graphs/object_detection_3d/obj_parser:ObjParser -- input_dir=[INTERMEDIATE_OUTPUT_DIR] output_dir=[OUTPUT_DIR]
+> ```
+> INPUT_DIR should be the folder with initial asset .obj files to be processed,
+> and OUTPUT_DIR is the folder where the processed asset .uuu file will be placed.
+>
+> Note: ObjParser combines all .obj files found in the given directory into a
+> single .uuu animation file, using the order given by sorting the filenames alphanumerically. Also the ObjParser directory inputs must be given as
+> absolute paths, not relative paths. See parser utility library at [`mediapipe/graphs/object_detection_3d/obj_parser/`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/object_detection_3d/obj_parser/) for more details.
+
 ## Resources
 
 *   Google Developers Blog:

docs/solutions/iris.md

@@ -69,7 +69,7 @@ and renders using a dedicated
 The
 [face landmark subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_landmark/face_landmark_front_gpu.pbtxt)
 internally uses a
-[face detection subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_front_gpu.pbtxt)
+[face detection subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range_gpu.pbtxt)
 from the
 [face detection module](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection).
 
@@ -193,7 +193,17 @@ on how to build MediaPipe examples.
 
 ### Web
 
-Please refer to [these instructions](../index.md#mediapipe-on-the-web).
+You can use the following links to load a demo in the MediaPipe Visualizer, and
+over there click the "Runner" icon in the top bar like shown below. The demos
+use your webcam video as input, which is processed all locally in real-time and
+never leaves your device. Please see
+[MediaPipe on the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html)
+in Google Developers Blog for details.
+
+![visualizer_runner](../images/visualizer_runner.png)
+
+*   [MediaPipe Iris](https://viz.mediapipe.dev/demo/iris_tracking)
+*   [MediaPipe Iris: Depth-from-Iris](https://viz.mediapipe.dev/demo/iris_depth)
 
 ## Resources
 

docs/solutions/knift.md

@@ -2,7 +2,7 @@
 layout: default
 title: KNIFT (Template-based Feature Matching)
 parent: Solutions
-nav_order: 12
+nav_order: 13
 ---
 
 # MediaPipe KNIFT

docs/solutions/media_sequence.md

@@ -2,7 +2,7 @@
 layout: default
 title: Dataset Preparation with MediaSequence
 parent: Solutions
-nav_order: 14
+nav_order: 15
 ---
 
 # Dataset Preparation with MediaSequence

docs/solutions/models.md

@@ -14,12 +14,27 @@ nav_order: 30
 
 ### [Face Detection](https://google.github.io/mediapipe/solutions/face_detection)
 
-*   Face detection model for front-facing/selfie camera:
-    [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/face_detection_front.tflite),
-    [TFLite model quantized for EdgeTPU/Coral](https://github.com/google/mediapipe/tree/master/mediapipe/examples/coral/models/face-detector-quantized_edgetpu.tflite)
-*   Face detection model for back-facing camera:
-    [TFLite model ](https://github.com/google/mediapipe/tree/master/mediapipe/models/face_detection_back.tflite)
-*   [Model card](https://mediapipe.page.link/blazeface-mc)
+*   Short-range model (best for faces within 2 meters from the camera):
+    [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range.tflite),
+    [TFLite model quantized for EdgeTPU/Coral](https://github.com/google/mediapipe/tree/master/mediapipe/examples/coral/models/face-detector-quantized_edgetpu.tflite),
+    [Model card](https://mediapipe.page.link/blazeface-mc)
+*   Full-range model (dense, best for faces within 5 meters from the camera):
+    [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_full_range.tflite),
+    [Model card](https://mediapipe.page.link/blazeface-back-mc)
+*   Full-range model (sparse, best for faces within 5 meters from the camera):
+    [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_full_range_sparse.tflite),
+    [Model card](https://mediapipe.page.link/blazeface-back-sparse-mc)
+
+Full-range dense and sparse models have the same quality in terms of
+[F-score](https://en.wikipedia.org/wiki/F-score) however differ in underlying
+metrics. The dense model is slightly better in
+[Recall](https://en.wikipedia.org/wiki/Precision_and_recall) whereas the sparse
+model outperforms the dense one in
+[Precision](https://en.wikipedia.org/wiki/Precision_and_recall). Speed-wise
+sparse model is ~30% faster when executing on CPU via
+[XNNPACK](https://github.com/google/XNNPACK) whereas on GPU the models
+demonstrate comparable latencies. Depending on your application, you may prefer
+one over the other.
 
 ### [Face Mesh](https://google.github.io/mediapipe/solutions/face_mesh)
 
@@ -41,17 +56,18 @@ nav_order: 30
     [TF.js model](https://tfhub.dev/mediapipe/handdetector/1)
 *   Hand landmark model:
     [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/hand_landmark/hand_landmark.tflite),
+    [TFLite model (sparse)](https://github.com/google/mediapipe/tree/master/mediapipe/modules/hand_landmark/hand_landmark_sparse.tflite),
     [TF.js model](https://tfhub.dev/mediapipe/handskeleton/1)
-*   [Model card](https://mediapipe.page.link/handmc)
+*   [Model card](https://mediapipe.page.link/handmc), [Model card (sparse)](https://mediapipe.page.link/handmc-sparse)
 
 ### [Pose](https://google.github.io/mediapipe/solutions/pose)
 
 *   Pose detection model:
     [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/pose_detection/pose_detection.tflite)
-*   Full-body pose landmark model:
-    [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/pose_landmark/pose_landmark_full_body.tflite)
-*   Upper-body pose landmark model:
-    [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/pose_landmark/pose_landmark_upper_body.tflite)
+*   Pose landmark model:
+    [TFLite model (lite)](https://github.com/google/mediapipe/tree/master/mediapipe/modules/pose_landmark/pose_landmark_lite.tflite),
+    [TFLite model (full)](https://github.com/google/mediapipe/tree/master/mediapipe/modules/pose_landmark/pose_landmark_full.tflite),
+    [TFLite model (heavy)](https://github.com/google/mediapipe/tree/master/mediapipe/modules/pose_landmark/pose_landmark_heavy.tflite)
 *   [Model card](https://mediapipe.page.link/blazepose-mc)
 
 ### [Holistic](https://google.github.io/mediapipe/solutions/holistic)
@@ -59,6 +75,12 @@ nav_order: 30
 *   Hand recrop model:
     [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/holistic_landmark/hand_recrop.tflite)
 
+### [Selfie Segmentation](https://google.github.io/mediapipe/solutions/selfie_segmentation)
+
+*   [TFLite model (general)](https://github.com/google/mediapipe/tree/master/mediapipe/modules/selfie_segmentation/selfie_segmentation.tflite)
+*   [TFLite model (landscape)](https://github.com/google/mediapipe/tree/master/mediapipe/modules/selfie_segmentation/selfie_segmentation_landscape.tflite)
+*   [Model card](https://mediapipe.page.link/selfiesegmentation-mc)
+
 ### [Hair Segmentation](https://google.github.io/mediapipe/solutions/hair_segmentation)
 
 *   [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/hair_segmentation.tflite)
@@ -73,12 +95,12 @@ nav_order: 30
 
 ### [Objectron](https://google.github.io/mediapipe/solutions/objectron)
 
-*   [TFLite model for shoes](https://github.com/google/mediapipe/tree/master/mediapipe/models/object_detection_3d_sneakers.tflite)
-*   [TFLite model for chairs](https://github.com/google/mediapipe/tree/master/mediapipe/models/object_detection_3d_chair.tflite)
-*   [TFLite model for cameras](https://github.com/google/mediapipe/tree/master/mediapipe/models/object_detection_3d_camera.tflite)
-*   [TFLite model for cups](https://github.com/google/mediapipe/tree/master/mediapipe/models/object_detection_3d_cup.tflite)
-*   [Single-stage TFLite model for shoes](https://github.com/google/mediapipe/tree/master/mediapipe/models/object_detection_3d_sneakers_1stage.tflite)
-*   [Single-stage TFLite model for chairs](https://github.com/google/mediapipe/tree/master/mediapipe/models/object_detection_3d_chair_1stage.tflite)
+*   [TFLite model for shoes](https://github.com/google/mediapipe/tree/master/mediapipe/modules/objectron/object_detection_3d_sneakers.tflite)
+*   [TFLite model for chairs](https://github.com/google/mediapipe/tree/master/mediapipe/modules/objectron/object_detection_3d_chair.tflite)
+*   [TFLite model for cameras](https://github.com/google/mediapipe/tree/master/mediapipe/modules/objectron/object_detection_3d_camera.tflite)
+*   [TFLite model for cups](https://github.com/google/mediapipe/tree/master/mediapipe/modules/objectron/object_detection_3d_cup.tflite)
+*   [Single-stage TFLite model for shoes](https://github.com/google/mediapipe/tree/master/mediapipe/modules/objectron/object_detection_3d_sneakers_1stage.tflite)
+*   [Single-stage TFLite model for chairs](https://github.com/google/mediapipe/tree/master/mediapipe/modules/objectron/object_detection_3d_chair_1stage.tflite)
 *   [Model card](https://mediapipe.page.link/objectron-mc)
 
 ### [KNIFT](https://google.github.io/mediapipe/solutions/knift)

docs/solutions/object_detection.md

@@ -2,7 +2,7 @@
 layout: default
 title: Object Detection
 parent: Solutions
-nav_order: 8
+nav_order: 9
 ---
 
 # MediaPipe Object Detection

docs/solutions/objectron.md

@@ -2,7 +2,7 @@
 layout: default
 title: Objectron (3D Object Detection)
 parent: Solutions
-nav_order: 11
+nav_order: 12
 ---
 
 # MediaPipe Objectron
@@ -186,18 +186,277 @@ trained our 3D object detection models. The technical details of the Objectron
 dataset, including usage and tutorials, are available on
 the [dataset website](https://github.com/google-research-datasets/Objectron/).
 
+## Solution APIs
+
+### Cross-platform Configuration Options
+
+Naming style and availability may differ slightly across platforms/languages.
+
+#### static_image_mode
+
+If set to `false`, the solution treats the input images as a video stream. It
+will try to detect objects in the very first images, and upon successful
+detection further localizes the 3D bounding box landmarks. In subsequent images,
+once all [max_num_objects](#max_num_objects) objects are detected and the
+corresponding 3D bounding box landmarks are localized, it simply tracks those
+landmarks without invoking another detection until it loses track of any of the
+objects. This reduces latency and is ideal for processing video frames. If set
+to `true`, object detection runs every input image, ideal for processing a batch
+of static, possibly unrelated, images. Default to `false`.
+
+#### max_num_objects
+
+Maximum number of objects to detect. Default to `5`.
+
+#### min_detection_confidence
+
+Minimum confidence value (`[0.0, 1.0]`) from the object-detection model for the
+detection to be considered successful. Default to `0.5`.
+
+#### min_tracking_confidence
+
+Minimum confidence value (`[0.0, 1.0]`) from the landmark-tracking model for the
+3D bounding box landmarks to be considered tracked successfully, or otherwise
+object detection will be invoked automatically on the next input image. Setting
+it to a higher value can increase robustness of the solution, at the expense of
+a higher latency. Ignored if [static_image_mode](#static_image_mode) is `true`,
+where object detection simply runs on every image. Default to `0.99`.
+
+#### model_name
+
+Name of the model to use for predicting 3D bounding box landmarks. Currently
+supports `{'Shoe', 'Chair', 'Cup', 'Camera'}`. Default to `Shoe`.
+
+#### focal_length
+
+By default, camera focal length defined in [NDC space](#ndc-space), i.e., `(fx,
+fy)`. Default to `(1.0, 1.0)`. To specify focal length in
+[pixel space](#pixel-space) instead, i.e., `(fx_pixel, fy_pixel)`, users should
+provide [`image_size`](#image_size) = `(image_width, image_height)` to enable
+conversions inside the API. For further details about NDC and pixel space,
+please see [Coordinate Systems](#coordinate-systems).
+
+#### principal_point
+
+By default, camera principal point defined in [NDC space](#ndc-space), i.e.,
+`(px, py)`. Default to `(0.0, 0.0)`. To specify principal point in
+[pixel space](#pixel-space), i.e.,`(px_pixel, py_pixel)`, users should provide
+[`image_size`](#image_size) = `(image_width, image_height)` to enable
+conversions inside the API. For further details about NDC and pixel space,
+please see [Coordinate Systems](#coordinate-systems).
+
+#### image_size
+
+**Specify only when [`focal_length`](#focal_length) and
+[`principal_point`](#principal_point) are specified in pixel space.**
+
+Size of the input image, i.e., `(image_width, image_height)`.
+
+### Output
+
+<!-- Naming style may differ slightly across platforms/languages. -->
+
+#### detected_objects
+
+A list of detected 3D bounding box. Each 3D bounding box consists of the
+following:
+
+*   `landmarks_2d` : 2D landmarks of the object's 3D bounding box. The landmark
+    coordinates are normalized to `[0.0, 1.0]` by the image width and height
+    respectively.
+
+*   `landmarks_3d` : 3D landmarks of the object's 3D bounding box. The landmark
+    coordinates are represented in [camera coordinate](#camera-coordinate)
+    frame.
+
+*   `rotation` : rotation matrix from object coordinate frame to camera
+    coordinate frame.
+
+*   `translation` : translation vector from object coordinate frame to camera
+    coordinate frame.
+
+*   `scale` : relative scale of the object along `x`, `y` and `z` directions.
+
+## Python Solution API
+
+Please first follow general [instructions](../getting_started/python.md) to
+install MediaPipe Python package, then learn more in the companion
+[Python Colab](#resources) and the usage example below.
+
+Supported configuration options:
+
+*   [static_image_mode](#static_image_mode)
+*   [max_num_objects](#max_num_objects)
+*   [min_detection_confidence](#min_detection_confidence)
+*   [min_tracking_confidence](#min_tracking_confidence)
+*   [model_name](#model_name)
+*   [focal_length](#focal_length)
+*   [principal_point](#principal_point)
+*   [image_size](#image_size)
+
+```python
+import cv2
+import mediapipe as mp
+mp_drawing = mp.solutions.drawing_utils
+mp_objectron = mp.solutions.objectron
+
+# For static images:
+IMAGE_FILES = []
+with mp_objectron.Objectron(static_image_mode=True,
+                            max_num_objects=5,
+                            min_detection_confidence=0.5,
+                            model_name='Shoe') as objectron:
+  for idx, file in enumerate(IMAGE_FILES):
+    image = cv2.imread(file)
+    # Convert the BGR image to RGB and process it with MediaPipe Objectron.
+    results = objectron.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+
+    # Draw box landmarks.
+    if not results.detected_objects:
+      print(f'No box landmarks detected on {file}')
+      continue
+    print(f'Box landmarks of {file}:')
+    annotated_image = image.copy()
+    for detected_object in results.detected_objects:
+      mp_drawing.draw_landmarks(
+          annotated_image, detected_object.landmarks_2d, mp_objectron.BOX_CONNECTIONS)
+      mp_drawing.draw_axis(annotated_image, detected_object.rotation,
+                           detected_object.translation)
+      cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
+
+# For webcam input:
+cap = cv2.VideoCapture(0)
+with mp_objectron.Objectron(static_image_mode=False,
+                            max_num_objects=5,
+                            min_detection_confidence=0.5,
+                            min_tracking_confidence=0.99,
+                            model_name='Shoe') as objectron:
+  while cap.isOpened():
+    success, image = cap.read()
+    if not success:
+      print("Ignoring empty camera frame.")
+      # If loading a video, use 'break' instead of 'continue'.
+      continue
+
+    # Convert the BGR image to RGB.
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    # To improve performance, optionally mark the image as not writeable to
+    # pass by reference.
+    image.flags.writeable = False
+    results = objectron.process(image)
+
+    # Draw the box landmarks on the image.
+    image.flags.writeable = True
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    if results.detected_objects:
+        for detected_object in results.detected_objects:
+            mp_drawing.draw_landmarks(
+              image, detected_object.landmarks_2d, mp_objectron.BOX_CONNECTIONS)
+            mp_drawing.draw_axis(image, detected_object.rotation,
+                                 detected_object.translation)
+    cv2.imshow('MediaPipe Objectron', image)
+    if cv2.waitKey(5) & 0xFF == 27:
+      break
+cap.release()
+```
+
+## JavaScript Solution API
+
+Please first see general [introduction](../getting_started/javascript.md) on
+MediaPipe in JavaScript, then learn more in the companion [web demo](#resources)
+and the following usage example.
+
+Supported configuration options:
+
+*   [staticImageMode](#static_image_mode)
+*   [maxNumObjects](#max_num_objects)
+*   [minDetectionConfidence](#min_detection_confidence)
+*   [minTrackingConfidence](#min_tracking_confidence)
+*   [modelName](#model_name)
+*   [focalLength](#focal_length)
+*   [principalPoint](#principal_point)
+*   [imageSize](#image_size)
+
+```html
+<!DOCTYPE html>
+<html>
+<head>
+  <meta charset="utf-8">
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/camera_utils/camera_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/control_utils/control_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/control_utils_3d.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/drawing_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/objectron/objectron.js" crossorigin="anonymous"></script>
+</head>
+
+<body>
+  <div class="container">
+    <video class="input_video"></video>
+    <canvas class="output_canvas" width="1280px" height="720px"></canvas>
+  </div>
+</body>
+</html>
+```
+
+```javascript
+<script type="module">
+const videoElement = document.getElementsByClassName('input_video')[0];
+const canvasElement = document.getElementsByClassName('output_canvas')[0];
+const canvasCtx = canvasElement.getContext('2d');
+
+function onResults(results) {
+  canvasCtx.save();
+  canvasCtx.drawImage(
+      results.image, 0, 0, canvasElement.width, canvasElement.height);
+  if (!!results.objectDetections) {
+    for (const detectedObject of results.objectDetections) {
+      // Reformat keypoint information as landmarks, for easy drawing.
+      const landmarks: mpObjectron.Point2D[] =
+          detectedObject.keypoints.map(x => x.point2d);
+      // Draw bounding box.
+      drawingUtils.drawConnectors(canvasCtx, landmarks,
+          mpObjectron.BOX_CONNECTIONS, {color: '#FF0000'});
+      // Draw centroid.
+      drawingUtils.drawLandmarks(canvasCtx, [landmarks[0]], {color: '#FFFFFF'});
+    }
+  }
+  canvasCtx.restore();
+}
+
+const objectron = new Objectron({locateFile: (file) => {
+  return `https://cdn.jsdelivr.net/npm/@mediapipe/objectron/${file}`;
+}});
+objectron.setOptions({
+  modelName: 'Chair',
+  maxNumObjects: 3,
+});
+objectron.onResults(onResults);
+
+const camera = new Camera(videoElement, {
+  onFrame: async () => {
+    await objectron.send({image: videoElement});
+  },
+  width: 1280,
+  height: 720
+});
+camera.start();
+</script>
+```
+
 ## Example Apps
 
 Please first see general instructions for
-[Android](../getting_started/android.md) and [iOS](../getting_started/ios.md) on
-how to build MediaPipe examples.
+[Android](../getting_started/android.md), [iOS](../getting_started/ios.md), and
+[desktop](../getting_started/cpp.md) on how to build MediaPipe examples.
 
 Note: To visualize a graph, copy the graph and paste it into
 [MediaPipe Visualizer](https://viz.mediapipe.dev/). For more information on how
 to visualize its associated subgraphs, please see
 [visualizer documentation](../tools/visualizer.md).
 
-### Two-stage Objectron
+### Mobile
+
+#### Two-stage Objectron
 
 *   Graph:
     [`mediapipe/graphs/object_detection_3d/object_occlusion_tracking.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/object_detection_3d/object_occlusion_tracking.pbtxt)
@@ -235,7 +494,7 @@ to visualize its associated subgraphs, please see
 
 *   iOS target: Not available
 
-### Single-stage Objectron
+#### Single-stage Objectron
 
 *   Graph:
     [`mediapipe/graphs/object_detection_3d/object_occlusion_tracking_1stage.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/object_detection_3d/object_occlusion_tracking.pbtxt)
@@ -259,15 +518,145 @@ to visualize its associated subgraphs, please see
 
 *   iOS target: Not available
 
+#### Assets
+
+Example app bounding boxes are rendered with [GlAnimationOverlayCalculator](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/object_detection_3d/calculators/gl_animation_overlay_calculator.cc) using a parsing of the sequenced .obj file
+ format into a custom .uuu format. This can be done for user assets as follows:
+> First run
+>
+> ```shell
+> ./mediapipe/graphs/object_detection_3d/obj_parser/obj_cleanup.sh [INPUT_DIR] [INTERMEDIATE_OUTPUT_DIR]
+> ```
+> and then run
+>
+> ```bash
+> bazel run -c opt mediapipe/graphs/object_detection_3d/obj_parser:ObjParser -- input_dir=[INTERMEDIATE_OUTPUT_DIR] output_dir=[OUTPUT_DIR]
+> ```
+> INPUT_DIR should be the folder with initial asset .obj files to be processed,
+> and OUTPUT_DIR is the folder where the processed asset .uuu file will be placed.
+>
+> Note: ObjParser combines all .obj files found in the given directory into a
+> single .uuu animation file, using the order given by sorting the filenames alphanumerically. Also the ObjParser directory inputs must be given as
+> absolute paths, not relative paths. See parser utility library at [`mediapipe/graphs/object_detection_3d/obj_parser/`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/object_detection_3d/obj_parser/) for more details.
+
+
+### Desktop
+
+To build the application, run:
+
+```bash
+bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 mediapipe/examples/desktop/object_detection_3d:objectron_cpu
+```
+
+To run the application, replace `<input video path>` and `<output video path>`
+in the command below with your own paths, and `<landmark model path>` and
+`<allowed labels>` with the following:
+
+Category | `<landmark model path>`                                                     | `<allowed labels>`
+:------- | :-------------------------------------------------------------------------- | :-----------------
+Shoe     | mediapipe/modules/objectron/object_detection_3d_sneakers.tflite | Footwear
+Chair    | mediapipe/modules/objectron/object_detection_3d_chair.tflite    | Chair
+Cup      | mediapipe/modules/objectron/object_detection_3d_cup.tflite      | Mug
+Camera   | mediapipe/modules/objectron/object_detection_3d_camera.tflite   | Camera
+
+```
+GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/object_detection_3d/objectron_cpu \
+  --calculator_graph_config_file=mediapipe/graphs/object_detection_3d/objectron_desktop_cpu.pbtxt \
+  --input_side_packets=input_video_path=<input video path>,output_video_path=<output video path>,box_landmark_model_path=<landmark model path>,allowed_labels=<allowed labels>
+```
+
+## Coordinate Systems
+
+### Object Coordinate
+
+Each object has its object coordinate frame. We use the below object coordinate
+definition, with `+x` pointing right, `+y` pointing up and `+z` pointing front,
+origin is at the center of the 3D bounding box.
+
+![box_coordinate.svg](../images/box_coordinate.svg)
+
+### Camera Coordinate
+
+A 3D object is parameterized by its `scale` and `rotation`, `translation` with
+regard to the camera coordinate frame. In this API we use the below camera
+coordinate definition, with `+x` pointing right, `+y` pointing up and `-z`
+pointing to the scene.
+
+![camera_coordinate.svg](../images/camera_coordinate.svg)
+
+To work with box landmarks, one can first derive landmark coordinates in object
+frame by scaling a origin centered unit box with `scale`, then transform to
+camera frame by applying `rotation` and `translation`:
+
+```
+landmarks_3d = rotation * scale * unit_box + translation
+```
+
+### NDC Space
+
+In this API we use
+[NDC(normalized device coordinates)](http://www.songho.ca/opengl/gl_projectionmatrix.html)
+as an intermediate space when projecting points from 3D to 2D. In NDC space,
+`x`, `y` are confined to `[-1, 1]`.
+
+![ndc_coordinate.svg](../images/ndc_coordinate.svg)
+
+By default the camera parameters `(fx, fy)` and `(px, py)` are defined in NDC
+space. Given `(X, Y, Z)` of 3D points in camera coordinate, one can project 3D
+points to NDC space as follows:
+
+```
+x_ndc = -fx * X / Z + px
+y_ndc = -fy * Y / Z + py
+z_ndc = 1 / Z
+```
+
+### Pixel Space
+
+In this API we set upper-left coner of an image as the origin of pixel
+coordinate. One can convert from NDC to pixel space as follows:
+
+```
+x_pixel = (1 + x_ndc) / 2.0 * image_width
+y_pixel = (1 - y_ndc) / 2.0 * image_height
+```
+
+Alternatively one can directly project from camera coordinate to pixel
+coordinate with camera parameters `(fx_pixel, fy_pixel)` and `(px_pixel,
+py_pixel)` defined in pixel space as follows:
+
+```
+x_pixel = -fx_pixel * X / Z + px_pixel
+y_pixel =  fy_pixel * Y / Z + py_pixel
+```
+
+Conversion of camera parameters from pixel space to NDC space:
+
+```
+fx = fx_pixel * 2.0 / image_width
+fy = fy_pixel * 2.0 / image_height
+```
+
+```
+px = -px_pixel * 2.0 / image_width  + 1.0
+py = -py_pixel * 2.0 / image_height + 1.0
+```
+
 ## Resources
 
 *   Google AI Blog:
     [Announcing the Objectron Dataset](https://ai.googleblog.com/2020/11/announcing-objectron-dataset.html)
 *   Google AI Blog:
     [Real-Time 3D Object Detection on Mobile Devices with MediaPipe](https://ai.googleblog.com/2020/03/real-time-3d-object-detection-on-mobile.html)
+*   Paper: [Objectron: A Large Scale Dataset of Object-Centric Videos in the
+    Wild with Pose Annotations](https://arxiv.org/abs/2012.09988), to appear in
+    CVPR 2021
 *   Paper: [MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak
     Shape Supervision](https://arxiv.org/abs/2003.03522)
 *   Paper:
     [Instant 3D Object Tracking with Applications in Augmented Reality](https://drive.google.com/open?id=1O_zHmlgXIzAdKljp20U_JUkEHOGG52R8)
-    ([presentation](https://www.youtube.com/watch?v=9ndF1AIo7h0))
+    ([presentation](https://www.youtube.com/watch?v=9ndF1AIo7h0)), Fourth
+    Workshop on Computer Vision for AR/VR, CVPR 2020
 *   [Models and model cards](./models.md#objectron)
+*   [Web demo](https://code.mediapipe.dev/codepen/objectron)
+*   [Python Colab](https://mediapipe.page.link/objectron_py_colab)

docs/solutions/pose.md

@@ -2,6 +2,8 @@
 layout: default
 title: Pose
 parent: Solutions
+has_children: true
+has_toc: false
 nav_order: 5
 ---
 
@@ -21,25 +23,26 @@ nav_order: 5
 ## Overview
 
 Human pose estimation from video plays a critical role in various applications
-such as quantifying physical exercises, sign language recognition, and full-body
-gesture control. For example, it can form the basis for yoga, dance, and fitness
-applications. It can also enable the overlay of digital content and information
-on top of the physical world in augmented reality.
+such as [quantifying physical exercises](./pose_classification.md), sign
+language recognition, and full-body gesture control. For example, it can form
+the basis for yoga, dance, and fitness applications. It can also enable the
+overlay of digital content and information on top of the physical world in
+augmented reality.
 
 MediaPipe Pose is a ML solution for high-fidelity body pose tracking, inferring
-33 2D landmarks on the whole body (or 25 upper-body landmarks) from RGB video
-frames utilizing our
+33 3D landmarks and background segmentation mask on the whole body from RGB
+video frames utilizing our
 [BlazePose](https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html)
 research that also powers the
 [ML Kit Pose Detection API](https://developers.google.com/ml-kit/vision/pose-detection).
 Current state-of-the-art approaches rely primarily on powerful desktop
 environments for inference, whereas our method achieves real-time performance on
 most modern [mobile phones](#mobile), [desktops/laptops](#desktop), in
-[python](#python) and even on the [web](#web).
+[python](#python-solution-api) and even on the [web](#javascript-solution-api).
 
-![pose_tracking_upper_body_example.gif](../images/mobile/pose_tracking_upper_body_example.gif) |
-:--------------------------------------------------------------------------------------------: |
-*Fig 1. Example of MediaPipe Pose for upper-body pose tracking.*                               |
+![pose_tracking_example.gif](../images/mobile/pose_tracking_example.gif) |
+:----------------------------------------------------------------------: |
+*Fig 1. Example of MediaPipe Pose for pose tracking.*                    |
 
 ## ML Pipeline
 
@@ -47,11 +50,11 @@ The solution utilizes a two-step detector-tracker ML pipeline, proven to be
 effective in our [MediaPipe Hands](./hands.md) and
 [MediaPipe Face Mesh](./face_mesh.md) solutions. Using a detector, the pipeline
 first locates the person/pose region-of-interest (ROI) within the frame. The
-tracker subsequently predicts the pose landmarks within the ROI using the
-ROI-cropped frame as input. Note that for video use cases the detector is
-invoked only as needed, i.e., for the very first frame and when the tracker
-could no longer identify body pose presence in the previous frame. For other
-frames the pipeline simply derives the ROI from the previous frame’s pose
+tracker subsequently predicts the pose landmarks and segmentation mask within
+the ROI using the ROI-cropped frame as input. Note that for video use cases the
+detector is invoked only as needed, i.e., for the very first frame and when the
+tracker could no longer identify body pose presence in the previous frame. For
+other frames the pipeline simply derives the ROI from the previous frame’s pose
 landmarks.
 
 The pipeline is implemented as a MediaPipe
@@ -74,6 +77,36 @@ Note: To visualize a graph, copy the graph and paste it into
 to visualize its associated subgraphs, please see
 [visualizer documentation](../tools/visualizer.md).
 
+## Pose Estimation Quality
+
+To evaluate the quality of our [models](./models.md#pose) against other
+well-performing publicly available solutions, we use three different validation
+datasets, representing different verticals: Yoga, Dance and HIIT. Each image
+contains only a single person located 2-4 meters from the camera. To be
+consistent with other solutions, we perform evaluation only for 17 keypoints
+from [COCO topology](https://cocodataset.org/#keypoints-2020).
+
+Method                                                                                                | Yoga <br/> [`mAP`] | Yoga <br/> [`[email protected]`] | Dance <br/> [`mAP`] | Dance <br/> [`[email protected]`] | HIIT <br/> [`mAP`] | HIIT <br/> [`[email protected]`]
+----------------------------------------------------------------------------------------------------- | -----------------: | ---------------------: | ------------------: | ----------------------: | -----------------: | ---------------------:
+BlazePose.Heavy                                                                                       | 68.1               | **96.4**               | 73.0                | **97.2**                | 74.0               | **97.5**
+BlazePose.Full                                                                                        | 62.6               | **95.5**               | 67.4                | **96.3**                | 68.0               | **95.7**
+BlazePose.Lite                                                                                        | 45.0               | **90.2**               | 53.6                | **92.5**                | 53.8               | **93.5**
+[AlphaPose.ResNet50](https://github.com/MVIG-SJTU/AlphaPose)                                          | 63.4               | **96.0**               | 57.8                | **95.5**                | 63.4               | **96.0**
+[Apple.Vision](https://developer.apple.com/documentation/vision/detecting_human_body_poses_in_images) | 32.8               | **82.7**               | 36.4                | **91.4**                | 44.5               | **88.6**
+
+![pose_tracking_pck_chart.png](../images/mobile/pose_tracking_pck_chart.png) |
+:--------------------------------------------------------------------------: |
+*Fig 2. Quality evaluation in [`[email protected]`].*                                  |
+
+We designed our models specifically for live perception use cases, so all of
+them work in real-time on the majority of modern devices.
+
+Method          | Latency <br/> Pixel 3 [TFLite GPU](https://www.tensorflow.org/lite/performance/gpu_advanced) | Latency <br/> MacBook Pro (15-inch 2017)
+--------------- | -------------------------------------------------------------------------------------------: | ---------------------------------------:
+BlazePose.Heavy | 53 ms                                                                                        | 38 ms
+BlazePose.Full  | 25 ms                                                                                        | 27 ms
+BlazePose.Lite  | 20 ms                                                                                        | 25 ms
+
 ## Models
 
 ### Person/pose Detection Model (BlazePose Detector)
@@ -90,25 +123,25 @@ hip midpoints.
 
 ![pose_tracking_detector_vitruvian_man.png](../images/mobile/pose_tracking_detector_vitruvian_man.png) |
 :----------------------------------------------------------------------------------------------------: |
-*Fig 2. Vitruvian man aligned via two virtual keypoints predicted by BlazePose detector in addition to the face bounding box.* |
+*Fig 3. Vitruvian man aligned via two virtual keypoints predicted by BlazePose detector in addition to the face bounding box.* |
 
-### Pose Landmark Model (BlazePose Tracker)
+### Pose Landmark Model (BlazePose GHUM 3D)
 
-The landmark model in MediaPipe Pose comes in two versions: a full-body model
-that predicts the location of 33 pose landmarks (see figure below), and an
-upper-body version that only predicts the first 25. The latter may be more
-accurate than the former in scenarios where the lower-body parts are mostly out
-of view.
-
-Please find more detail in the
-[BlazePose Google AI Blog](https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html),
-this [paper](https://arxiv.org/abs/2006.10204) and
-[the model card](./models.md#pose), and the attributes in each landmark
-[below](#pose_landmarks).
+The landmark model in MediaPipe Pose predicts the location of 33 pose landmarks
+(see figure below).
 
 ![pose_tracking_full_body_landmarks.png](../images/mobile/pose_tracking_full_body_landmarks.png) |
 :----------------------------------------------------------------------------------------------: |
-*Fig 3. 33 pose landmarks.*                                                                      |
+*Fig 4. 33 pose landmarks.*                                                                      |
+
+Optionally, MediaPipe Pose can predicts a full-body
+[segmentation mask](#segmentation_mask) represented as a two-class segmentation
+(human or background).
+
+Please find more detail in the
+[BlazePose Google AI Blog](https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html),
+this [paper](https://arxiv.org/abs/2006.10204),
+[the model card](./models.md#pose) and the [Output](#output) section below.
 
 ## Solution APIs
 
@@ -126,12 +159,11 @@ until it loses track, on reducing computation and latency. If set to `true`,
 person detection runs every input image, ideal for processing a batch of static,
 possibly unrelated, images. Default to `false`.
 
-#### upper_body_only
+#### model_complexity
 
-If set to `true`, the solution outputs only the 25 upper-body pose landmarks.
-Otherwise, it outputs the full set of 33 pose landmarks. Note that
-upper-body-only prediction may be more accurate for use cases where the
-lower-body parts are mostly out of view. Default to `false`.
+Complexity of the pose landmark model: `0`, `1` or `2`. Landmark accuracy as
+well as inference latency generally go up with the model complexity. Default to
+`1`.
 
 #### smooth_landmarks
 
@@ -139,6 +171,18 @@ If set to `true`, the solution filters pose landmarks across different input
 images to reduce jitter, but ignored if [static_image_mode](#static_image_mode)
 is also set to `true`. Default to `true`.
 
+#### enable_segmentation
+
+If set to `true`, in addition to the pose landmarks the solution also generates
+the segmentation mask. Default to `false`.
+
+#### smooth_segmentation
+
+If set to `true`, the solution filters segmentation masks across different input
+images to reduce jitter. Ignored if [enable_segmentation](#enable_segmentation)
+is `false` or [static_image_mode](#static_image_mode) is `true`. Default to
+`true`.
+
 #### min_detection_confidence
 
 Minimum confidence value (`[0.0, 1.0]`) from the person-detection model for the
@@ -159,26 +203,56 @@ Naming style may differ slightly across platforms/languages.
 
 #### pose_landmarks
 
-A list of pose landmarks. Each lanmark consists of the following:
+A list of pose landmarks. Each landmark consists of the following:
 
 *   `x` and `y`: Landmark coordinates normalized to `[0.0, 1.0]` by the image
     width and height respectively.
-*   `z`: Should be discarded as currently the model is not fully trained to
-    predict depth, but this is something on the roadmap.
+*   `z`: Represents the landmark depth with the depth at the midpoint of hips
+    being the origin, and the smaller the value the closer the landmark is to
+    the camera. The magnitude of `z` uses roughly the same scale as `x`.
 *   `visibility`: A value in `[0.0, 1.0]` indicating the likelihood of the
     landmark being visible (present and not occluded) in the image.
 
+#### pose_world_landmarks
+
+*Fig 5. Example of MediaPipe Pose real-world 3D coordinates.* |
+:-----------------------------------------------------------: |
+<video autoplay muted loop preload style="height: auto; width: 480px"><source src="../images/mobile/pose_world_landmarks.mp4" type="video/mp4"></video> |
+
+Another list of pose landmarks in world coordinates. Each landmark consists of
+the following:
+
+*   `x`, `y` and `z`: Real-world 3D coordinates in meters with the origin at the
+    center between hips.
+*   `visibility`: Identical to that defined in the corresponding
+    [pose_landmarks](#pose_landmarks).
+
+#### segmentation_mask
+
+The output segmentation mask, predicted only when
+[enable_segmentation](#enable_segmentation) is set to `true`. The mask has the
+same width and height as the input image, and contains values in `[0.0, 1.0]`
+where `1.0` and `0.0` indicate high certainty of a "human" and "background"
+pixel respectively. Please refer to the platform-specific usage examples below
+for usage details.
+
+*Fig 6. Example of MediaPipe Pose segmentation mask.* |
+:-----------------------------------------------------------: |
+<video autoplay muted loop preload style="height: auto; width: 480px"><source src="../images/mobile/pose_segmentation.mp4" type="video/mp4"></video> |
+
 ### Python Solution API
 
 Please first follow general [instructions](../getting_started/python.md) to
-install MediaPipe Python package, then learn more in the companion [Colab] and
-the following usage example.
+install MediaPipe Python package, then learn more in the companion
+[Python Colab](#resources) and the usage example below.
 
 Supported configuration options:
 
 *   [static_image_mode](#static_image_mode)
-*   [upper_body_only](#upper_body_only)
+*   [model_complexity](#model_complexity)
 *   [smooth_landmarks](#smooth_landmarks)
+*   [enable_segmentation](#enable_segmentation)
+*   [smooth_segmentation](#smooth_segmentation)
 *   [min_detection_confidence](#min_detection_confidence)
 *   [min_tracking_confidence](#min_tracking_confidence)
 
@@ -186,72 +260,96 @@ Supported configuration options:
 import cv2
 import mediapipe as mp
 mp_drawing = mp.solutions.drawing_utils
+mp_drawing_styles = mp.solutions.drawing_styles
 mp_pose = mp.solutions.pose
 
 # For static images:
-pose = mp_pose.Pose(
-    static_image_mode=True, min_detection_confidence=0.5)
-for idx, file in enumerate(file_list):
-  image = cv2.imread(file)
-  image_hight, image_width, _ = image.shape
-  # Convert the BGR image to RGB before processing.
-  results = pose.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+IMAGE_FILES = []
+BG_COLOR = (192, 192, 192) # gray
+with mp_pose.Pose(
+    static_image_mode=True,
+    model_complexity=2,
+    enable_segmentation=True,
+    min_detection_confidence=0.5) as pose:
+  for idx, file in enumerate(IMAGE_FILES):
+    image = cv2.imread(file)
+    image_height, image_width, _ = image.shape
+    # Convert the BGR image to RGB before processing.
+    results = pose.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
 
-  if not results.pose_landmarks:
-    continue
-  print(
-      f'Nose coordinates: ('
-      f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].x * image_width}, '
-      f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].y * image_hight})'
-  )
-  # Draw pose landmarks on the image.
-  annotated_image = image.copy()
-  mp_drawing.draw_landmarks(
-      annotated_image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS)
-  cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
-pose.close()
+    if not results.pose_landmarks:
+      continue
+    print(
+        f'Nose coordinates: ('
+        f'{results.pose_landmarks.landmark[mp_pose.PoseLandmark.NOSE].x * image_width}, '
+        f'{results.pose_landmarks.landmark[mp_pose.PoseLandmark.NOSE].y * image_height})'
+    )
+
+    annotated_image = image.copy()
+    # Draw segmentation on the image.
+    # To improve segmentation around boundaries, consider applying a joint
+    # bilateral filter to "results.segmentation_mask" with "image".
+    condition = np.stack((results.segmentation_mask,) * 3, axis=-1) > 0.1
+    bg_image = np.zeros(image.shape, dtype=np.uint8)
+    bg_image[:] = BG_COLOR
+    annotated_image = np.where(condition, annotated_image, bg_image)
+    # Draw pose landmarks on the image.
+    mp_drawing.draw_landmarks(
+        annotated_image,
+        results.pose_landmarks,
+        mp_pose.POSE_CONNECTIONS,
+        landmark_drawing_spec=mp_drawing_styles.get_default_pose_landmarks_style())
+    cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
+    # Plot pose world landmarks.
+    mp_drawing.plot_landmarks(
+        results.pose_world_landmarks, mp_pose.POSE_CONNECTIONS)
 
 # For webcam input:
-pose = mp_pose.Pose(
-    min_detection_confidence=0.5, min_tracking_confidence=0.5)
 cap = cv2.VideoCapture(0)
-while cap.isOpened():
-  success, image = cap.read()
-  if not success:
-    print("Ignoring empty camera frame.")
-    # If loading a video, use 'break' instead of 'continue'.
-    continue
+with mp_pose.Pose(
+    min_detection_confidence=0.5,
+    min_tracking_confidence=0.5) as pose:
+  while cap.isOpened():
+    success, image = cap.read()
+    if not success:
+      print("Ignoring empty camera frame.")
+      # If loading a video, use 'break' instead of 'continue'.
+      continue
 
-  # Flip the image horizontally for a later selfie-view display, and convert
-  # the BGR image to RGB.
-  image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
-  # To improve performance, optionally mark the image as not writeable to
-  # pass by reference.
-  image.flags.writeable = False
-  results = pose.process(image)
+    # Flip the image horizontally for a later selfie-view display, and convert
+    # the BGR image to RGB.
+    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
+    # To improve performance, optionally mark the image as not writeable to
+    # pass by reference.
+    image.flags.writeable = False
+    results = pose.process(image)
 
-  # Draw the pose annotation on the image.
-  image.flags.writeable = True
-  image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-  mp_drawing.draw_landmarks(
-      image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS)
-  cv2.imshow('MediaPipe Pose', image)
-  if cv2.waitKey(5) & 0xFF == 27:
-    break
-pose.close()
+    # Draw the pose annotation on the image.
+    image.flags.writeable = True
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    mp_drawing.draw_landmarks(
+        image,
+        results.pose_landmarks,
+        mp_pose.POSE_CONNECTIONS,
+        landmark_drawing_spec=mp_drawing_styles.get_default_pose_landmarks_style())
+    cv2.imshow('MediaPipe Pose', image)
+    if cv2.waitKey(5) & 0xFF == 27:
+      break
 cap.release()
 ```
 
 ### JavaScript Solution API
 
 Please first see general [introduction](../getting_started/javascript.md) on
-MediaPipe in JavaScript, then learn more in the companion [web demo] and the
-following usage example.
+MediaPipe in JavaScript, then learn more in the companion [web demo](#resources)
+and the following usage example.
 
 Supported configuration options:
 
-*   [upperBodyOnly](#upper_body_only)
+*   [modelComplexity](#model_complexity)
 *   [smoothLandmarks](#smooth_landmarks)
+*   [enableSegmentation](#enable_segmentation)
+*   [smoothSegmentation](#smooth_segmentation)
 *   [minDetectionConfidence](#min_detection_confidence)
 *   [minTrackingConfidence](#min_tracking_confidence)
 
@@ -262,6 +360,7 @@ Supported configuration options:
   <meta charset="utf-8">
   <script src="https://cdn.jsdelivr.net/npm/@mediapipe/camera_utils/camera_utils.js" crossorigin="anonymous"></script>
   <script src="https://cdn.jsdelivr.net/npm/@mediapipe/control_utils/control_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/control_utils_3d.js" crossorigin="anonymous"></script>
   <script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/drawing_utils.js" crossorigin="anonymous"></script>
   <script src="https://cdn.jsdelivr.net/npm/@mediapipe/pose/pose.js" crossorigin="anonymous"></script>
 </head>
@@ -270,6 +369,7 @@ Supported configuration options:
   <div class="container">
     <video class="input_video"></video>
     <canvas class="output_canvas" width="1280px" height="720px"></canvas>
+    <div class="landmark-grid-container"></div>
   </div>
 </body>
 </html>
@@ -280,25 +380,48 @@ Supported configuration options:
 const videoElement = document.getElementsByClassName('input_video')[0];
 const canvasElement = document.getElementsByClassName('output_canvas')[0];
 const canvasCtx = canvasElement.getContext('2d');
+const landmarkContainer = document.getElementsByClassName('landmark-grid-container')[0];
+const grid = new LandmarkGrid(landmarkContainer);
 
 function onResults(results) {
+  if (!results.poseLandmarks) {
+    grid.updateLandmarks([]);
+    return;
+  }
+
   canvasCtx.save();
   canvasCtx.clearRect(0, 0, canvasElement.width, canvasElement.height);
+  canvasCtx.drawImage(results.segmentationMask, 0, 0,
+                      canvasElement.width, canvasElement.height);
+
+  // Only overwrite existing pixels.
+  canvasCtx.globalCompositeOperation = 'source-in';
+  canvasCtx.fillStyle = '#00FF00';
+  canvasCtx.fillRect(0, 0, canvasElement.width, canvasElement.height);
+
+  // Only overwrite missing pixels.
+  canvasCtx.globalCompositeOperation = 'destination-atop';
   canvasCtx.drawImage(
       results.image, 0, 0, canvasElement.width, canvasElement.height);
+
+  canvasCtx.globalCompositeOperation = 'source-over';
   drawConnectors(canvasCtx, results.poseLandmarks, POSE_CONNECTIONS,
                  {color: '#00FF00', lineWidth: 4});
   drawLandmarks(canvasCtx, results.poseLandmarks,
                 {color: '#FF0000', lineWidth: 2});
   canvasCtx.restore();
+
+  grid.updateLandmarks(results.poseWorldLandmarks);
 }
 
 const pose = new Pose({locateFile: (file) => {
   return `https://cdn.jsdelivr.net/npm/@mediapipe/pose/${file}`;
 }});
 pose.setOptions({
-  upperBodyOnly: false,
+  modelComplexity: 1,
   smoothLandmarks: true,
+  enableSegmentation: true,
+  smoothSegmentation: true,
   minDetectionConfidence: 0.5,
   minTrackingConfidence: 0.5
 });
@@ -338,16 +461,6 @@ to visualize its associated subgraphs, please see
 *   iOS target:
     [`mediapipe/examples/ios/posetrackinggpu:PoseTrackingGpuApp`](http:/mediapipe/examples/ios/posetrackinggpu/BUILD)
 
-#### Upper-body Only
-
-*   Graph:
-    [`mediapipe/graphs/pose_tracking/upper_body_pose_tracking_gpu.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/pose_tracking/upper_body_pose_tracking_gpu.pbtxt)
-*   Android target:
-    [(or download prebuilt ARM64 APK)](https://drive.google.com/file/d/1uKc6T7KSuA0Mlq2URi5YookHu0U3yoh_/view?usp=sharing)
-    [`mediapipe/examples/android/src/java/com/google/mediapipe/apps/upperbodyposetrackinggpu:upperbodyposetrackinggpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/upperbodyposetrackinggpu/BUILD)
-*   iOS target:
-    [`mediapipe/examples/ios/upperbodyposetrackinggpu:UpperBodyPoseTrackingGpuApp`](http:/mediapipe/examples/ios/upperbodyposetrackinggpu/BUILD)
-
 ### Desktop
 
 Please first see general instructions for [desktop](../getting_started/cpp.md)
@@ -366,19 +479,6 @@ on how to build MediaPipe examples.
     *   Target:
         [`mediapipe/examples/desktop/pose_tracking:pose_tracking_gpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/pose_tracking/BUILD)
 
-#### Upper-body Only
-
-*   Running on CPU
-    *   Graph:
-        [`mediapipe/graphs/pose_tracking/upper_body_pose_tracking_cpu.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/pose_tracking/upper_body_pose_tracking_cpu.pbtxt)
-    *   Target:
-        [`mediapipe/examples/desktop/upper_body_pose_tracking:upper_body_pose_tracking_cpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/upper_body_pose_tracking/BUILD)
-*   Running on GPU
-    *   Graph:
-        [`mediapipe/graphs/pose_tracking/upper_body_pose_tracking_gpu.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/pose_tracking/upper_body_pose_tracking_gpu.pbtxt)
-    *   Target:
-        [`mediapipe/examples/desktop/upper_body_pose_tracking:upper_body_pose_tracking_gpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/upper_body_pose_tracking/BUILD)
-
 ## Resources
 
 *   Google AI Blog:
@@ -387,7 +487,8 @@ on how to build MediaPipe examples.
     [BlazePose: On-device Real-time Body Pose Tracking](https://arxiv.org/abs/2006.10204)
     ([presentation](https://youtu.be/YPpUOTRn5tA))
 *   [Models and model cards](./models.md#pose)
+*   [Web demo](https://code.mediapipe.dev/codepen/pose)
+*   [Python Colab](https://mediapipe.page.link/pose_py_colab)
 
-[Colab]:https://mediapipe.page.link/pose_py_colab
-
-[web demo]:https://code.mediapipe.dev/codepen/pose
+[`mAP`]: https://cocodataset.org/#keypoints-eval
+[`[email protected]`]: https://github.com/cbsudux/Human-Pose-Estimation-101

docs/solutions/pose_classification.md

@@ -0,0 +1,145 @@
+---
+layout: default
+title: Pose Classification
+parent: Pose
+grand_parent: Solutions
+nav_order: 1
+---
+
+# Pose Classification
+{: .no_toc }
+
+<details close markdown="block">
+  <summary>
+    Table of contents
+  </summary>
+  {: .text-delta }
+1. TOC
+{:toc}
+</details>
+---
+
+## Overview
+
+One of the applications
+[BlazePose](https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html)
+can enable is fitness. More specifically - pose classification and repetition
+counting. In this section we'll provide basic guidance on building a custom pose
+classifier with the help of [Colabs](#colabs) and wrap it in a simple fitness
+demo within
+[ML Kit quickstart app](https://developers.google.com/ml-kit/vision/pose-detection/classifying-poses#4_integrate_with_the_ml_kit_quickstart_app).
+Push-ups and squats are used for demonstration purposes as the most common
+exercises.
+
+![pose_classification_pushups_and_squats.gif](../images/mobile/pose_classification_pushups_and_squats.gif) |
+:--------------------------------------------------------------------------------------------------------: |
+*Fig 1. Pose classification and repetition counting with MediaPipe Pose.*                                  |
+
+We picked the
+[k-nearest neighbors algorithm](https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm)
+(k-NN) as the classifier. It's simple and easy to start with. The algorithm
+determines the object's class based on the closest samples in the training set.
+
+**To build it, one needs to:**
+
+1.  Collect image samples of the target exercises and run pose prediction on
+    them,
+2.  Convert obtained pose landmarks to a representation suitable for the k-NN
+    classifier and form a training set using these [Colabs](#colabs),
+3.  Perform the classification itself followed by repetition counting (e.g., in
+    the
+    [ML Kit quickstart app](https://developers.google.com/ml-kit/vision/pose-detection/classifying-poses#4_integrate_with_the_ml_kit_quickstart_app)).
+
+## Training Set
+
+To build a good classifier appropriate samples should be collected for the
+training set: about a few hundred samples for each terminal state of each
+exercise (e.g., "up" and "down" positions for push-ups). It's important that
+collected samples cover different camera angles, environment conditions, body
+shapes, and exercise variations.
+
+![pose_classification_pushups_un_and_down_samples.jpg](../images/mobile/pose_classification_pushups_un_and_down_samples.jpg) |
+:--------------------------------------------------------------------------------------------------------------------------: |
+*Fig 2. Two terminal states of push-ups.*                                                                                    |
+
+To transform samples into a k-NN classifier training set, both
+[`Pose Classification Colab (Basic)`] and
+[`Pose Classification Colab (Extended)`] could be used. They use the
+[Python Solution API](./pose.md#python-solution-api) to run the BlazePose models
+on given images and dump predicted pose landmarks to a CSV file. Additionally,
+the [`Pose Classification Colab (Extended)`] provides useful tools to find
+outliers (e.g., wrongly predicted poses) and underrepresented classes (e.g., not
+covering all camera angles) by classifying each sample against the entire
+training set. After that, you'll be able to test the classifier on an arbitrary
+video right in the Colab.
+
+## Classification
+
+Code of the classifier is available both in the
+[`Pose Classification Colab (Extended)`] and in the
+[ML Kit quickstart app](https://developers.google.com/ml-kit/vision/pose-detection/classifying-poses#4_integrate_with_the_ml_kit_quickstart_app).
+Please refer to them for details of the approach described below.
+
+The k-NN algorithm used for pose classification requires a feature vector
+representation of each sample and a metric to compute the distance between two
+such vectors to find the nearest pose samples to a target one.
+
+To convert pose landmarks to a feature vector, we use pairwise distances between
+predefined lists of pose joints, such as distances between wrist and shoulder,
+ankle and hip, and two wrists. Since the algorithm relies on distances, all
+poses are normalized to have the same torso size and vertical torso orientation
+before the conversion.
+
+![pose_classification_pairwise_distances.png](../images/mobile/pose_classification_pairwise_distances.png) |
+:--------------------------------------------------------------------------------------------------------: |
+*Fig 3. Main pairwise distances used for the pose feature vector.*                                         |
+
+To get a better classification result, k-NN search is invoked twice with
+different distance metrics:
+
+*   First, to filter out samples that are almost the same as the target one but
+    have only a few different values in the feature vector (which means
+    differently bent joints and thus other pose class), minimum per-coordinate
+    distance is used as distance metric,
+*   Then average per-coordinate distance is used to find the nearest pose
+    cluster among those from the first search.
+
+Finally, we apply
+[exponential moving average](https://en.wikipedia.org/wiki/Moving_average#Exponential_moving_average)
+(EMA) smoothing to level any noise from pose prediction or classification. To do
+that, we search not only for the nearest pose cluster, but we calculate a
+probability for each of them and use it for smoothing over time.
+
+## Repetition Counting
+
+To count the repetitions, the algorithm monitors the probability of a target
+pose class. Let's take push-ups with its "up" and "down" terminal states:
+
+*   When the probability of the "down" pose class passes a certain threshold for
+    the first time, the algorithm marks that the "down" pose class is entered.
+*   Once the probability drops below the threshold, the algorithm marks that the
+    "down" pose class has been exited and increases the counter.
+
+To avoid cases when the probability fluctuates around the threshold (e.g., when
+the user pauses between "up" and "down" states) causing phantom counts, the
+threshold used to detect when the state is exited is actually slightly lower
+than the one used to detect when the state is entered. It creates an interval
+where the pose class and the counter can't be changed.
+
+## Future Work
+
+We are actively working on improving
+[BlazePose GHUM 3D](./pose.md#pose-landmark-model-blazepose-ghum-3d)'s Z
+prediction. It will allow us to use joint angles in the feature vectors, which
+are more natural and easier to configure (although distances can still be useful
+to detect touches between body parts) and to perform rotation normalization of
+poses and reduce the number of camera angles required for accurate k-NN
+classification.
+
+## Colabs
+
+*   [`Pose Classification Colab (Basic)`]
+*   [`Pose Classification Colab (Extended)`]
+
+[`Pose Classification Colab (Basic)`]: https://mediapipe.page.link/pose_classification_basic
+[`Pose Classification Colab (Extended)`]: https://mediapipe.page.link/pose_classification_extended

docs/solutions/selfie_segmentation.md

@@ -0,0 +1,290 @@
+---
+layout: default
+title: Selfie Segmentation
+parent: Solutions
+nav_order: 7
+---
+
+# MediaPipe Selfie Segmentation
+{: .no_toc }
+
+<details close markdown="block">
+  <summary>
+    Table of contents
+  </summary>
+  {: .text-delta }
+1. TOC
+{:toc}
+</details>
+---
+
+## Overview
+
+*Fig 1. Example of MediaPipe Selfie Segmentation.* |
+:------------------------------------------------: |
+<video autoplay muted loop preload style="height: auto; width: 480px"><source src="../images/selfie_segmentation_web.mp4" type="video/mp4"></video> |
+
+MediaPipe Selfie Segmentation segments the prominent humans in the scene. It can
+run in real-time on both smartphones and laptops. The intended use cases include
+selfie effects and video conferencing, where the person is close (< 2m) to the
+camera.
+
+## Models
+
+In this solution, we provide two models: general and landscape. Both models are
+based on
+[MobileNetV3](https://ai.googleblog.com/2019/11/introducing-next-generation-on-device.html),
+with modifications to make them more efficient. The general model operates on a
+256x256x3 (HWC) tensor, and outputs a 256x256x1 tensor representing the
+segmentation mask. The landscape model is similar to the general model, but
+operates on a 144x256x3 (HWC) tensor. It has fewer FLOPs than the general model,
+and therefore, runs faster. Note that MediaPipe Selfie Segmentation
+automatically resizes the input image to the desired tensor dimension before
+feeding it into the ML models.
+
+The general model is also powering
+[ML Kit](https://developers.google.com/ml-kit/vision/selfie-segmentation), and a
+variant of the landscape model is powering
+[Google Meet](https://ai.googleblog.com/2020/10/background-features-in-google-meet.html).
+Please find more detail about the models in the
+[model card](./models.md#selfie-segmentation).
+
+## ML Pipeline
+
+The pipeline is implemented as a MediaPipe
+[graph](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/selfie_segmentation/selfie_segmentation_gpu.pbtxt)
+that uses a
+[selfie segmentation subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/selfie_segmentation/selfie_segmentation_gpu.pbtxt)
+from the
+[selfie segmentation module](https://github.com/google/mediapipe/tree/master/mediapipe/modules/selfie_segmentation).
+
+Note: To visualize a graph, copy the graph and paste it into
+[MediaPipe Visualizer](https://viz.mediapipe.dev/). For more information on how
+to visualize its associated subgraphs, please see
+[visualizer documentation](../tools/visualizer.md).
+
+## Solution APIs
+
+### Cross-platform Configuration Options
+
+Naming style and availability may differ slightly across platforms/languages.
+
+#### model_selection
+
+An integer index `0` or `1`. Use `0` to select the general model, and `1` to
+select the landscape model (see details in [Models](#models)). Default to `0` if
+not specified.
+
+### Output
+
+Naming style may differ slightly across platforms/languages.
+
+#### segmentation_mask
+
+The output segmentation mask, which has the same dimension as the input image.
+
+### Python Solution API
+
+Please first follow general [instructions](../getting_started/python.md) to
+install MediaPipe Python package, then learn more in the companion
+[Python Colab](#resources) and the usage example below.
+
+Supported configuration options:
+
+*   [model_selection](#model_selection)
+
+```python
+import cv2
+import mediapipe as mp
+import numpy as np
+mp_drawing = mp.solutions.drawing_utils
+mp_selfie_segmentation = mp.solutions.selfie_segmentation
+
+# For static images:
+IMAGE_FILES = []
+BG_COLOR = (192, 192, 192) # gray
+MASK_COLOR = (255, 255, 255) # white
+with mp_selfie_segmentation.SelfieSegmentation(
+    model_selection=0) as selfie_segmentation:
+  for idx, file in enumerate(IMAGE_FILES):
+    image = cv2.imread(file)
+    image_height, image_width, _ = image.shape
+    # Convert the BGR image to RGB before processing.
+    results = selfie_segmentation.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+
+    # Draw selfie segmentation on the background image.
+    # To improve segmentation around boundaries, consider applying a joint
+    # bilateral filter to "results.segmentation_mask" with "image".
+    condition = np.stack((results.segmentation_mask,) * 3, axis=-1) > 0.1
+    # Generate solid color images for showing the output selfie segmentation mask.
+    fg_image = np.zeros(image.shape, dtype=np.uint8)
+    fg_image[:] = MASK_COLOR
+    bg_image = np.zeros(image.shape, dtype=np.uint8)
+    bg_image[:] = BG_COLOR
+    output_image = np.where(condition, fg_image, bg_image)
+    cv2.imwrite('/tmp/selfie_segmentation_output' + str(idx) + '.png', output_image)
+
+# For webcam input:
+BG_COLOR = (192, 192, 192) # gray
+cap = cv2.VideoCapture(0)
+with mp_selfie_segmentation.SelfieSegmentation(
+    model_selection=1) as selfie_segmentation:
+  bg_image = None
+  while cap.isOpened():
+    success, image = cap.read()
+    if not success:
+      print("Ignoring empty camera frame.")
+      # If loading a video, use 'break' instead of 'continue'.
+      continue
+
+    # Flip the image horizontally for a later selfie-view display, and convert
+    # the BGR image to RGB.
+    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
+    # To improve performance, optionally mark the image as not writeable to
+    # pass by reference.
+    image.flags.writeable = False
+    results = selfie_segmentation.process(image)
+
+    image.flags.writeable = True
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+
+    # Draw selfie segmentation on the background image.
+    # To improve segmentation around boundaries, consider applying a joint
+    # bilateral filter to "results.segmentation_mask" with "image".
+    condition = np.stack(
+      (results.segmentation_mask,) * 3, axis=-1) > 0.1
+    # The background can be customized.
+    #   a) Load an image (with the same width and height of the input image) to
+    #      be the background, e.g., bg_image = cv2.imread('/path/to/image/file')
+    #   b) Blur the input image by applying image filtering, e.g.,
+    #      bg_image = cv2.GaussianBlur(image,(55,55),0)
+    if bg_image is None:
+      bg_image = np.zeros(image.shape, dtype=np.uint8)
+      bg_image[:] = BG_COLOR
+    output_image = np.where(condition, image, bg_image)
+
+    cv2.imshow('MediaPipe Selfie Segmentation', output_image)
+    if cv2.waitKey(5) & 0xFF == 27:
+      break
+cap.release()
+```
+
+### JavaScript Solution API
+
+Please first see general [introduction](../getting_started/javascript.md) on
+MediaPipe in JavaScript, then learn more in the companion [web demo](#resources)
+and the following usage example.
+
+Supported configuration options:
+
+*   [modelSelection](#model_selection)
+
+```html
+<!DOCTYPE html>
+<html>
+<head>
+  <meta charset="utf-8">
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/camera_utils/camera_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/control_utils/control_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/drawing_utils.js" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/@mediapipe/selfie_segmentation/selfie_segmentation.js" crossorigin="anonymous"></script>
+</head>
+
+<body>
+  <div class="container">
+    <video class="input_video"></video>
+    <canvas class="output_canvas" width="1280px" height="720px"></canvas>
+  </div>
+</body>
+</html>
+```
+
+```javascript
+<script type="module">
+const videoElement = document.getElementsByClassName('input_video')[0];
+const canvasElement = document.getElementsByClassName('output_canvas')[0];
+const canvasCtx = canvasElement.getContext('2d');
+
+function onResults(results) {
+  canvasCtx.save();
+  canvasCtx.clearRect(0, 0, canvasElement.width, canvasElement.height);
+  canvasCtx.drawImage(results.segmentationMask, 0, 0,
+                      canvasElement.width, canvasElement.height);
+
+  // Only overwrite existing pixels.
+  canvasCtx.globalCompositeOperation = 'source-in';
+  canvasCtx.fillStyle = '#00FF00';
+  canvasCtx.fillRect(0, 0, canvasElement.width, canvasElement.height);
+
+  // Only overwrite missing pixels.
+  canvasCtx.globalCompositeOperation = 'destination-atop';
+  canvasCtx.drawImage(
+      results.image, 0, 0, canvasElement.width, canvasElement.height);
+
+  canvasCtx.restore();
+}
+
+const selfieSegmentation = new SelfieSegmentation({locateFile: (file) => {
+  return `https://cdn.jsdelivr.net/npm/@mediapipe/selfie_segmentation/${file}`;
+}});
+selfieSegmentation.setOptions({
+  modelSelection: 1,
+});
+selfieSegmentation.onResults(onResults);
+
+const camera = new Camera(videoElement, {
+  onFrame: async () => {
+    await selfieSegmentation.send({image: videoElement});
+  },
+  width: 1280,
+  height: 720
+});
+camera.start();
+</script>
+```
+
+## Example Apps
+
+Please first see general instructions for
+[Android](../getting_started/android.md), [iOS](../getting_started/ios.md), and
+[desktop](../getting_started/cpp.md) on how to build MediaPipe examples.
+
+Note: To visualize a graph, copy the graph and paste it into
+[MediaPipe Visualizer](https://viz.mediapipe.dev/). For more information on how
+to visualize its associated subgraphs, please see
+[visualizer documentation](../tools/visualizer.md).
+
+### Mobile
+
+*   Graph:
+    [`mediapipe/graphs/selfie_segmentation/selfie_segmentation_gpu.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/selfie_segmentation/selfie_segmentation_gpu.pbtxt)
+*   Android target:
+    [(or download prebuilt ARM64 APK)](https://drive.google.com/file/d/1DoeyGzMmWUsjfVgZfGGecrn7GKzYcEAo/view?usp=sharing)
+    [`mediapipe/examples/android/src/java/com/google/mediapipe/apps/selfiesegmentationgpu:selfiesegmentationgpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/selfiesegmentationgpu/BUILD)
+*   iOS target:
+    [`mediapipe/examples/ios/selfiesegmentationgpu:SelfieSegmentationGpuApp`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/ios/selfiesegmentationgpu/BUILD)
+
+### Desktop
+
+Please first see general instructions for [desktop](../getting_started/cpp.md)
+on how to build MediaPipe examples.
+
+*   Running on CPU
+    *   Graph:
+        [`mediapipe/graphs/selfie_segmentation/selfie_segmentation_cpu.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/selfie_segmentation/selfie_segmentation_cpu.pbtxt)
+    *   Target:
+        [`mediapipe/examples/desktop/selfie_segmentation:selfie_segmentation_cpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/selfie_segmentation/BUILD)
+*   Running on GPU
+    *   Graph:
+        [`mediapipe/graphs/selfie_segmentation/selfie_segmentation_gpu.pbtxt`](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/selfie_segmentation/selfie_segmentation_gpu.pbtxt)
+    *   Target:
+        [`mediapipe/examples/desktop/selfie_segmentation:selfie_segmentation_gpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/selfie_segmentation/BUILD)
+
+## Resources
+
+*   Google AI Blog:
+    [Background Features in Google Meet, Powered by Web ML](https://ai.googleblog.com/2020/10/background-features-in-google-meet.html)
+*   [ML Kit Selfie Segmentation API](https://developers.google.com/ml-kit/vision/selfie-segmentation)
+*   [Models and model cards](./models.md#selfie-segmentation)
+*   [Web demo](https://code.mediapipe.dev/codepen/selfie_segmentation)
+*   [Python Colab](https://mediapipe.page.link/selfie_segmentation_py_colab)

docs/solutions/solutions.md

@@ -13,22 +13,26 @@ has_toc: false
 {:toc}
 ---
 
+MediaPipe offers open source cross-platform, customizable ML solutions for live
+and streaming media.
+
 <!-- []() in the first cell is needed to preserve table formatting in GitHub Pages. -->
 <!-- Whenever this table is updated, paste a copy to ../external_index.md. -->
 
 []()                                                                                      | [Android](https://google.github.io/mediapipe/getting_started/android) | [iOS](https://google.github.io/mediapipe/getting_started/ios) | [C++](https://google.github.io/mediapipe/getting_started/cpp) | [Python](https://google.github.io/mediapipe/getting_started/python) | [JS](https://google.github.io/mediapipe/getting_started/javascript) | [Coral](https://github.com/google/mediapipe/tree/master/mediapipe/examples/coral/README.md)
 :---------------------------------------------------------------------------------------- | :-------------------------------------------------------------: | :-----------------------------------------------------: | :-----------------------------------------------------: | :-----------------------------------------------------------: | :-----------------------------------------------------------: | :--------------------------------------------------------------------:
-[Face Detection](https://google.github.io/mediapipe/solutions/face_detection)                   | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               | ✅
+[Face Detection](https://google.github.io/mediapipe/solutions/face_detection)                   | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             | ✅
 [Face Mesh](https://google.github.io/mediapipe/solutions/face_mesh)                             | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Iris](https://google.github.io/mediapipe/solutions/iris)                                       | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               |
 [Hands](https://google.github.io/mediapipe/solutions/hands)                                     | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Pose](https://google.github.io/mediapipe/solutions/pose)                                       | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Holistic](https://google.github.io/mediapipe/solutions/holistic)                               | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
+[Selfie Segmentation](https://google.github.io/mediapipe/solutions/selfie_segmentation)         | ✅                                                               | ✅                                                       | ✅                                                       | ✅                                                             | ✅                                                             |
 [Hair Segmentation](https://google.github.io/mediapipe/solutions/hair_segmentation)             | ✅                                                               |                                                         | ✅                                                       |                                                               |                                                               |
 [Object Detection](https://google.github.io/mediapipe/solutions/object_detection)               | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               | ✅
 [Box Tracking](https://google.github.io/mediapipe/solutions/box_tracking)                       | ✅                                                               | ✅                                                       | ✅                                                       |                                                               |                                                               |
 [Instant Motion Tracking](https://google.github.io/mediapipe/solutions/instant_motion_tracking) | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
-[Objectron](https://google.github.io/mediapipe/solutions/objectron)                             | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
+[Objectron](https://google.github.io/mediapipe/solutions/objectron)                             | ✅                                                               |                                                         | ✅                                                       | ✅                                                             | ✅                                                             |
 [KNIFT](https://google.github.io/mediapipe/solutions/knift)                                     | ✅                                                               |                                                         |                                                         |                                                               |                                                               |
 [AutoFlip](https://google.github.io/mediapipe/solutions/autoflip)                               |                                                                 |                                                         | ✅                                                       |                                                               |                                                               |
 [MediaSequence](https://google.github.io/mediapipe/solutions/media_sequence)                    |                                                                 |                                                         | ✅                                                       |                                                               |                                                               |

docs/solutions/youtube_8m.md

@@ -2,7 +2,7 @@
 layout: default
 title: YouTube-8M Feature Extraction and Model Inference
 parent: Solutions
-nav_order: 15
+nav_order: 16
 ---
 
 # YouTube-8M Feature Extraction and Model Inference

docs/tools/tracing_and_profiling.md

@@ -41,6 +41,7 @@ profiler_config {
   trace_enabled: true
   enable_profiler: true
   trace_log_interval_count: 200
+  trace_log_path: "/sdcard/Download/"
 }
 ```
 
@@ -64,7 +65,7 @@ MediaPipe will emit data into a pre-specified directory:
 
 *   On the desktop, this will be the `/tmp` directory.
 
-*   On Android, this will be the `/sdcard` directory.
+*   On Android, this will be the external storage directory (e.g., `/storage/emulated/0/`).
 
 *   On iOS, this can be reached through XCode. Select "Window/Devices and
     Simulators" and select the "Devices" tab.
@@ -103,7 +104,7 @@ we record ten intervals of half a second each. This can be overridden by adding
     *   Include the line below in your `AndroidManifest.xml` file.
 
         ```xml
-        <uses-permission android:name="android.permission.WRITE_EXTERNAL_STORAGE" />
+        <uses-permission android:name="android.permission.MANAGE_EXTERNAL_STORAGE" />
         ```
 
     *   Grant the permission either upon first app launch, or by going into
@@ -130,8 +131,8 @@ we record ten intervals of half a second each. This can be overridden by adding
     events to a trace log files at:
 
     ```bash
-    /sdcard/mediapipe_trace_0.binarypb
-    /sdcard/mediapipe_trace_1.binarypb
+    /storage/emulated/0/Download/mediapipe_trace_0.binarypb
+    /storage/emulated/0/Download/mediapipe_trace_1.binarypb
     ```
 
     After every 5 sec, writing shifts to a successive trace log file, such that
@@ -139,10 +140,10 @@ we record ten intervals of half a second each. This can be overridden by adding
     trace files have been written to the device using adb shell.
 
     ```bash
-    adb shell "ls -la /sdcard/"
+    adb shell "ls -la /storage/emulated/0/Download"
     ```
 
-    On android, MediaPipe selects the external storage directory `/sdcard` for
+    On android, MediaPipe selects the external storage (e.g., `/storage/emulated/0/`) for
     trace logs. This directory can be overridden using the setting
     `trace_log_path`, like:
 
@@ -150,7 +151,7 @@ we record ten intervals of half a second each. This can be overridden by adding
     profiler_config {
       trace_enabled: true
       enable_profiler: true
-      trace_log_path: "/sdcard/profiles/"
+      trace_log_path: "/sdcard/Download/profiles/"
     }
     ```
 
@@ -161,7 +162,7 @@ we record ten intervals of half a second each. This can be overridden by adding
 
     ```bash
     # from your terminal
-    adb pull /sdcard/mediapipe_trace_0.binarypb
+    adb pull /storage/emulated/0/Download/mediapipe_trace_0.binarypb
     # if successful you should see something like
     # /sdcard/mediapipe_trace_0.binarypb: 1 file pulled. 0.1 MB/s (6766 bytes in 0.045s)
     ```

docs/tools/visualizer.md

@@ -37,7 +37,7 @@ The graph can be modified by adding and editing code in the Editor view.
     ![New Button](../images/upload_button.png)
 
 *   Pressing the "Upload" button will prompt the user to select a local PBTXT
-    file, which will everwrite the current code within the editor.
+    file, which will overwrite the current code within the editor.
 
 *   Alternatively, code can be pasted directly into the editor window.
 

mediapipe/MediaPipe.tulsiproj/Configs/MediaPipe.tulsigen

@@ -2,39 +2,41 @@
   "additionalFilePaths" : [
     "/BUILD",
     "mediapipe/BUILD",
-    "mediapipe/objc/BUILD",
-    "mediapipe/framework/BUILD",
-    "mediapipe/gpu/BUILD",
-    "mediapipe/objc/testing/app/BUILD",
     "mediapipe/examples/ios/common/BUILD",
-    "mediapipe/examples/ios/helloworld/BUILD",
     "mediapipe/examples/ios/facedetectioncpu/BUILD",
     "mediapipe/examples/ios/facedetectiongpu/BUILD",
     "mediapipe/examples/ios/faceeffect/BUILD",
     "mediapipe/examples/ios/facemeshgpu/BUILD",
     "mediapipe/examples/ios/handdetectiongpu/BUILD",
     "mediapipe/examples/ios/handtrackinggpu/BUILD",
+    "mediapipe/examples/ios/helloworld/BUILD",
     "mediapipe/examples/ios/holistictrackinggpu/BUILD",
     "mediapipe/examples/ios/iristrackinggpu/BUILD",
     "mediapipe/examples/ios/objectdetectioncpu/BUILD",
     "mediapipe/examples/ios/objectdetectiongpu/BUILD",
+    "mediapipe/examples/ios/objectdetectiontrackinggpu/BUILD",
     "mediapipe/examples/ios/posetrackinggpu/BUILD",
-    "mediapipe/examples/ios/upperbodyposetrackinggpu/BUILD"
+    "mediapipe/examples/ios/selfiesegmentationgpu/BUILD",
+    "mediapipe/framework/BUILD",
+    "mediapipe/gpu/BUILD",
+    "mediapipe/objc/BUILD",
+    "mediapipe/objc/testing/app/BUILD"
   ],
   "buildTargets" : [
-    "//mediapipe/examples/ios/helloworld:HelloWorldApp",
     "//mediapipe/examples/ios/facedetectioncpu:FaceDetectionCpuApp",
     "//mediapipe/examples/ios/facedetectiongpu:FaceDetectionGpuApp",
     "//mediapipe/examples/ios/faceeffect:FaceEffectApp",
     "//mediapipe/examples/ios/facemeshgpu:FaceMeshGpuApp",
     "//mediapipe/examples/ios/handdetectiongpu:HandDetectionGpuApp",
     "//mediapipe/examples/ios/handtrackinggpu:HandTrackingGpuApp",
+    "//mediapipe/examples/ios/helloworld:HelloWorldApp",
     "//mediapipe/examples/ios/holistictrackinggpu:HolisticTrackingGpuApp",
     "//mediapipe/examples/ios/iristrackinggpu:IrisTrackingGpuApp",
     "//mediapipe/examples/ios/objectdetectioncpu:ObjectDetectionCpuApp",
     "//mediapipe/examples/ios/objectdetectiongpu:ObjectDetectionGpuApp",
+    "//mediapipe/examples/ios/objectdetectiontrackinggpu:ObjectDetectionTrackingGpuApp",
     "//mediapipe/examples/ios/posetrackinggpu:PoseTrackingGpuApp",
-    "//mediapipe/examples/ios/upperbodyposetrackinggpu:UpperBodyPoseTrackingGpuApp",
+    "//mediapipe/examples/ios/selfiesegmentationgpu:SelfieSegmentationGpuApp",
     "//mediapipe/objc:mediapipe_framework_ios"
   ],
   "optionSet" : {
@@ -91,19 +93,19 @@
     "mediapipe/examples/ios",
     "mediapipe/examples/ios/common",
     "mediapipe/examples/ios/common/Base.lproj",
-    "mediapipe/examples/ios/helloworld",
     "mediapipe/examples/ios/facedetectioncpu",
     "mediapipe/examples/ios/facedetectiongpu",
     "mediapipe/examples/ios/faceeffect",
     "mediapipe/examples/ios/faceeffect/Base.lproj",
     "mediapipe/examples/ios/handdetectiongpu",
     "mediapipe/examples/ios/handtrackinggpu",
+    "mediapipe/examples/ios/helloworld",
     "mediapipe/examples/ios/holistictrackinggpu",
     "mediapipe/examples/ios/iristrackinggpu",
     "mediapipe/examples/ios/objectdetectioncpu",
     "mediapipe/examples/ios/objectdetectiongpu",
     "mediapipe/examples/ios/posetrackinggpu",
-    "mediapipe/examples/ios/upperbodyposetrackinggpu",
+    "mediapipe/examples/ios/selfiesegmentationgpu",
     "mediapipe/framework",
     "mediapipe/framework/deps",
     "mediapipe/framework/formats",
@@ -121,6 +123,7 @@
     "mediapipe/graphs/hand_tracking",
     "mediapipe/graphs/object_detection",
     "mediapipe/graphs/pose_tracking",
+    "mediapipe/graphs/selfie_segmentation",
     "mediapipe/models",
     "mediapipe/modules",
     "mediapipe/objc",

mediapipe/MediaPipe.tulsiproj/project.tulsiconf

@@ -9,7 +9,6 @@
   "packages" : [
     "",
     "mediapipe",
-    "mediapipe/objc",
     "mediapipe/examples/ios",
     "mediapipe/examples/ios/facedetectioncpu",
     "mediapipe/examples/ios/facedetectiongpu",
@@ -21,8 +20,10 @@
     "mediapipe/examples/ios/iristrackinggpu",
     "mediapipe/examples/ios/objectdetectioncpu",
     "mediapipe/examples/ios/objectdetectiongpu",
+    "mediapipe/examples/ios/objectdetectiontrackinggpu",
     "mediapipe/examples/ios/posetrackinggpu",
-    "mediapipe/examples/ios/upperbodyposetrackinggpu"
+    "mediapipe/examples/ios/selfiesegmentationgpu",
+    "mediapipe/objc"
   ],
   "projectName" : "Mediapipe",
   "workspaceRoot" : "../.."

mediapipe/calculators/audio/BUILD

@@ -1,4 +1,4 @@
-# Copyright 2019 The MediaPipe Authors.
+# Copyright 2019, 2021 The MediaPipe Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -128,7 +128,7 @@ cc_library(
         "//mediapipe/framework/port:ret_check",
         "//mediapipe/util:time_series_util",
         "@com_google_absl//absl/strings",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -147,7 +147,7 @@ cc_library(
         "//mediapipe/util:time_series_util",
         "@com_google_absl//absl/strings",
         "@com_google_audio_tools//audio/dsp/mfcc",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -167,8 +167,8 @@ cc_library(
         "//mediapipe/util:time_series_util",
         "@com_google_absl//absl/strings",
         "@com_google_audio_tools//audio/dsp:resampler",
-        "@com_google_audio_tools//audio/dsp:resampler_rational_factor",
-        "@eigen_archive//:eigen",
+        "@com_google_audio_tools//audio/dsp:resampler_q",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -208,7 +208,7 @@ cc_library(
         "@com_google_absl//absl/strings",
         "@com_google_audio_tools//audio/dsp:window_functions",
         "@com_google_audio_tools//audio/dsp/spectrogram",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -228,7 +228,7 @@ cc_library(
         "//mediapipe/framework/port:status",
         "//mediapipe/util:time_series_util",
         "@com_google_audio_tools//audio/dsp:window_functions",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -244,6 +244,7 @@ cc_test(
         "//mediapipe/framework/formats:time_series_header_cc_proto",
         "//mediapipe/framework/port:gtest_main",
         "//mediapipe/framework/port:parse_text_proto",
+        "@com_google_absl//absl/flags:flag",
     ],
 )
 
@@ -260,7 +261,7 @@ cc_test(
         "//mediapipe/framework/port:integral_types",
         "//mediapipe/framework/port:parse_text_proto",
         "//mediapipe/util:time_series_test_util",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )
 
@@ -275,7 +276,7 @@ cc_test(
         "//mediapipe/framework/port:gtest_main",
         "//mediapipe/framework/port:status",
         "//mediapipe/util:time_series_test_util",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )
 
@@ -295,7 +296,7 @@ cc_test(
         "//mediapipe/framework/port:status",
         "//mediapipe/util:time_series_test_util",
         "@com_google_audio_tools//audio/dsp:number_util",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )
 
@@ -313,7 +314,7 @@ cc_test(
         "//mediapipe/framework/port:integral_types",
         "//mediapipe/framework/port:status",
         "//mediapipe/util:time_series_test_util",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )
 
@@ -332,7 +333,7 @@ cc_test(
         "//mediapipe/framework/port:status",
         "//mediapipe/util:time_series_test_util",
         "@com_google_audio_tools//audio/dsp:window_functions",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )
 
@@ -351,6 +352,6 @@ cc_test(
         "//mediapipe/framework/tool:validate_type",
         "//mediapipe/util:time_series_test_util",
         "@com_google_audio_tools//audio/dsp:signal_vector_util",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )

mediapipe/calculators/audio/audio_decoder_calculator.cc

@@ -48,17 +48,17 @@ namespace mediapipe {
 // TODO: support decoding multiple streams.
 class AudioDecoderCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc);
+  static absl::Status GetContract(CalculatorContract* cc);
 
-  mediapipe::Status Open(CalculatorContext* cc) override;
-  mediapipe::Status Process(CalculatorContext* cc) override;
-  mediapipe::Status Close(CalculatorContext* cc) override;
+  absl::Status Open(CalculatorContext* cc) override;
+  absl::Status Process(CalculatorContext* cc) override;
+  absl::Status Close(CalculatorContext* cc) override;
 
  private:
   std::unique_ptr<AudioDecoder> decoder_;
 };
 
-mediapipe::Status AudioDecoderCalculator::GetContract(CalculatorContract* cc) {
+absl::Status AudioDecoderCalculator::GetContract(CalculatorContract* cc) {
   cc->InputSidePackets().Tag("INPUT_FILE_PATH").Set<std::string>();
   if (cc->InputSidePackets().HasTag("OPTIONS")) {
     cc->InputSidePackets().Tag("OPTIONS").Set<mediapipe::AudioDecoderOptions>();
@@ -67,10 +67,10 @@ mediapipe::Status AudioDecoderCalculator::GetContract(CalculatorContract* cc) {
   if (cc->Outputs().HasTag("AUDIO_HEADER")) {
     cc->Outputs().Tag("AUDIO_HEADER").SetNone();
   }
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status AudioDecoderCalculator::Open(CalculatorContext* cc) {
+absl::Status AudioDecoderCalculator::Open(CalculatorContext* cc) {
   const std::string& input_file_path =
       cc->InputSidePackets().Tag("INPUT_FILE_PATH").Get<std::string>();
   const auto& decoder_options =
@@ -87,10 +87,10 @@ mediapipe::Status AudioDecoderCalculator::Open(CalculatorContext* cc) {
     cc->Outputs().Tag("AUDIO_HEADER").SetHeader(Adopt(header.release()));
   }
   cc->Outputs().Tag("AUDIO_HEADER").Close();
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status AudioDecoderCalculator::Process(CalculatorContext* cc) {
+absl::Status AudioDecoderCalculator::Process(CalculatorContext* cc) {
   Packet data;
   int options_index = -1;
   auto status = decoder_->GetData(&options_index, &data);
@@ -100,7 +100,7 @@ mediapipe::Status AudioDecoderCalculator::Process(CalculatorContext* cc) {
   return status;
 }
 
-mediapipe::Status AudioDecoderCalculator::Close(CalculatorContext* cc) {
+absl::Status AudioDecoderCalculator::Close(CalculatorContext* cc) {
   return decoder_->Close();
 }
 

mediapipe/calculators/audio/audio_decoder_calculator_test.cc

@@ -12,6 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+#include "absl/flags/flag.h"
 #include "mediapipe/framework/calculator_runner.h"
 #include "mediapipe/framework/deps/file_path.h"
 #include "mediapipe/framework/formats/time_series_header.pb.h"
@@ -24,7 +25,7 @@ namespace mediapipe {
 
 TEST(AudioDecoderCalculatorTest, TestWAV) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "AudioDecoderCalculator"
         input_side_packet: "INPUT_FILE_PATH:input_file_path"
         output_stream: "AUDIO:audio"
@@ -33,7 +34,7 @@ TEST(AudioDecoderCalculatorTest, TestWAV) {
           [type.googleapis.com/mediapipe.AudioDecoderOptions]: {
             audio_stream { stream_index: 0 }
           }
-        })");
+        })pb");
   CalculatorRunner runner(node_config);
   runner.MutableSidePackets()->Tag("INPUT_FILE_PATH") = MakePacket<std::string>(
       file::JoinPath("./",
@@ -55,7 +56,7 @@ TEST(AudioDecoderCalculatorTest, TestWAV) {
 
 TEST(AudioDecoderCalculatorTest, Test48KWAV) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "AudioDecoderCalculator"
         input_side_packet: "INPUT_FILE_PATH:input_file_path"
         output_stream: "AUDIO:audio"
@@ -64,7 +65,7 @@ TEST(AudioDecoderCalculatorTest, Test48KWAV) {
           [type.googleapis.com/mediapipe.AudioDecoderOptions]: {
             audio_stream { stream_index: 0 }
           }
-        })");
+        })pb");
   CalculatorRunner runner(node_config);
   runner.MutableSidePackets()->Tag("INPUT_FILE_PATH") = MakePacket<std::string>(
       file::JoinPath("./",
@@ -86,7 +87,7 @@ TEST(AudioDecoderCalculatorTest, Test48KWAV) {
 
 TEST(AudioDecoderCalculatorTest, TestMP3) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "AudioDecoderCalculator"
         input_side_packet: "INPUT_FILE_PATH:input_file_path"
         output_stream: "AUDIO:audio"
@@ -95,7 +96,7 @@ TEST(AudioDecoderCalculatorTest, TestMP3) {
           [type.googleapis.com/mediapipe.AudioDecoderOptions]: {
             audio_stream { stream_index: 0 }
           }
-        })");
+        })pb");
   CalculatorRunner runner(node_config);
   runner.MutableSidePackets()->Tag("INPUT_FILE_PATH") = MakePacket<std::string>(
       file::JoinPath("./",
@@ -117,7 +118,7 @@ TEST(AudioDecoderCalculatorTest, TestMP3) {
 
 TEST(AudioDecoderCalculatorTest, TestAAC) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "AudioDecoderCalculator"
         input_side_packet: "INPUT_FILE_PATH:input_file_path"
         output_stream: "AUDIO:audio"
@@ -126,7 +127,7 @@ TEST(AudioDecoderCalculatorTest, TestAAC) {
           [type.googleapis.com/mediapipe.AudioDecoderOptions]: {
             audio_stream { stream_index: 0 }
           }
-        })");
+        })pb");
   CalculatorRunner runner(node_config);
   runner.MutableSidePackets()->Tag("INPUT_FILE_PATH") = MakePacket<std::string>(
       file::JoinPath("./",

mediapipe/calculators/audio/basic_time_series_calculators.cc

@@ -38,7 +38,7 @@ static bool SafeMultiply(int x, int y, int* result) {
 }
 }  // namespace
 
-mediapipe::Status BasicTimeSeriesCalculatorBase::GetContract(
+absl::Status BasicTimeSeriesCalculatorBase::GetContract(
     CalculatorContract* cc) {
   cc->Inputs().Index(0).Set<Matrix>(
       // Input stream with TimeSeriesHeader.
@@ -46,10 +46,10 @@ mediapipe::Status BasicTimeSeriesCalculatorBase::GetContract(
   cc->Outputs().Index(0).Set<Matrix>(
       // Output stream with TimeSeriesHeader.
   );
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status BasicTimeSeriesCalculatorBase::Open(CalculatorContext* cc) {
+absl::Status BasicTimeSeriesCalculatorBase::Open(CalculatorContext* cc) {
   TimeSeriesHeader input_header;
   MP_RETURN_IF_ERROR(time_series_util::FillTimeSeriesHeaderIfValid(
       cc->Inputs().Index(0).Header(), &input_header));
@@ -57,11 +57,13 @@ mediapipe::Status BasicTimeSeriesCalculatorBase::Open(CalculatorContext* cc) {
   auto output_header = new TimeSeriesHeader(input_header);
   MP_RETURN_IF_ERROR(MutateHeader(output_header));
   cc->Outputs().Index(0).SetHeader(Adopt(output_header));
-  return mediapipe::OkStatus();
+
+  cc->SetOffset(0);
+
+  return absl::OkStatus();
 }
 
-mediapipe::Status BasicTimeSeriesCalculatorBase::Process(
-    CalculatorContext* cc) {
+absl::Status BasicTimeSeriesCalculatorBase::Process(CalculatorContext* cc) {
   const Matrix& input = cc->Inputs().Index(0).Get<Matrix>();
   MP_RETURN_IF_ERROR(time_series_util::IsMatrixShapeConsistentWithHeader(
       input, cc->Inputs().Index(0).Header().Get<TimeSeriesHeader>()));
@@ -71,12 +73,12 @@ mediapipe::Status BasicTimeSeriesCalculatorBase::Process(
       *output, cc->Outputs().Index(0).Header().Get<TimeSeriesHeader>()));
 
   cc->Outputs().Index(0).Add(output.release(), cc->InputTimestamp());
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status BasicTimeSeriesCalculatorBase::MutateHeader(
+absl::Status BasicTimeSeriesCalculatorBase::MutateHeader(
     TimeSeriesHeader* output_header) {
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
 // Calculator to sum an input time series across channels.  This is
@@ -86,9 +88,9 @@ mediapipe::Status BasicTimeSeriesCalculatorBase::MutateHeader(
 class SumTimeSeriesAcrossChannelsCalculator
     : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     output_header->set_num_channels(1);
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -104,9 +106,9 @@ REGISTER_CALCULATOR(SumTimeSeriesAcrossChannelsCalculator);
 class AverageTimeSeriesAcrossChannelsCalculator
     : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     output_header->set_num_channels(1);
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -122,7 +124,7 @@ REGISTER_CALCULATOR(AverageTimeSeriesAcrossChannelsCalculator);
 // Options proto: None.
 class SummarySaiToPitchogramCalculator : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     if (output_header->num_channels() != 1) {
       return tool::StatusInvalid(
           absl::StrCat("Expected single-channel input, got ",
@@ -131,7 +133,7 @@ class SummarySaiToPitchogramCalculator : public BasicTimeSeriesCalculatorBase {
     output_header->set_num_channels(output_header->num_samples());
     output_header->set_num_samples(1);
     output_header->set_sample_rate(output_header->packet_rate());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -160,7 +162,7 @@ REGISTER_CALCULATOR(ReverseChannelOrderCalculator);
 // Options proto: None.
 class FlattenPacketCalculator : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     const int num_input_channels = output_header->num_channels();
     const int num_input_samples = output_header->num_samples();
     RET_CHECK(num_input_channels >= 0)
@@ -174,7 +176,7 @@ class FlattenPacketCalculator : public BasicTimeSeriesCalculatorBase {
     output_header->set_num_channels(output_num_channels);
     output_header->set_num_samples(1);
     output_header->set_sample_rate(output_header->packet_rate());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -253,10 +255,10 @@ REGISTER_CALCULATOR(DivideByMeanAcrossChannelsCalculator);
 // Options proto: None.
 class MeanCalculator : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     output_header->set_num_samples(1);
     output_header->set_sample_rate(output_header->packet_rate());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -272,10 +274,10 @@ REGISTER_CALCULATOR(MeanCalculator);
 // Options proto: None.
 class StandardDeviationCalculator : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     output_header->set_num_samples(1);
     output_header->set_sample_rate(output_header->packet_rate());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -293,9 +295,9 @@ REGISTER_CALCULATOR(StandardDeviationCalculator);
 // Options proto: None.
 class CovarianceCalculator : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     output_header->set_num_samples(output_header->num_channels());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -313,9 +315,9 @@ REGISTER_CALCULATOR(CovarianceCalculator);
 // Options proto: None.
 class L2NormCalculator : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     output_header->set_num_channels(1);
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {
@@ -385,12 +387,12 @@ REGISTER_CALCULATOR(ElementwiseSquareCalculator);
 // Options proto: None.
 class FirstHalfSlicerCalculator : public BasicTimeSeriesCalculatorBase {
  protected:
-  mediapipe::Status MutateHeader(TimeSeriesHeader* output_header) final {
+  absl::Status MutateHeader(TimeSeriesHeader* output_header) final {
     const int num_input_samples = output_header->num_samples();
     RET_CHECK(num_input_samples >= 0)
         << "FirstHalfSlicerCalculator: num_input_samples < 0";
     output_header->set_num_samples(num_input_samples / 2);
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   Matrix ProcessMatrix(const Matrix& input_matrix) final {

mediapipe/calculators/audio/basic_time_series_calculators.h

@@ -28,16 +28,16 @@ namespace mediapipe {
 
 class BasicTimeSeriesCalculatorBase : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc);
-  mediapipe::Status Open(CalculatorContext* cc) override;
-  mediapipe::Status Process(CalculatorContext* cc) override;
+  static absl::Status GetContract(CalculatorContract* cc);
+  absl::Status Open(CalculatorContext* cc) final;
+  absl::Status Process(CalculatorContext* cc) final;
 
  protected:
   // Open() calls this method to mutate the output stream header.  The input
   // to this function will contain a copy of the input stream header, so
   // subclasses that do not need to mutate the header do not need to override
   // it.
-  virtual mediapipe::Status MutateHeader(TimeSeriesHeader* output_header);
+  virtual absl::Status MutateHeader(TimeSeriesHeader* output_header);
 
   // Process() calls this method on each packet to compute the output matrix.
   virtual Matrix ProcessMatrix(const Matrix& input_matrix) = 0;

mediapipe/calculators/audio/mfcc_mel_calculators.cc

@@ -66,7 +66,7 @@ std::string PortableDebugString(const TimeSeriesHeader& header) {
 // rows corresponding to the new feature space).
 class FramewiseTransformCalculatorBase : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).Set<Matrix>(
         // Sequence of Matrices, each column describing a particular time frame,
         // each row a feature dimension, with TimeSeriesHeader.
@@ -75,11 +75,11 @@ class FramewiseTransformCalculatorBase : public CalculatorBase {
         // Sequence of Matrices, each column describing a particular time frame,
         // each row a feature dimension, with TimeSeriesHeader.
     );
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override;
-  mediapipe::Status Process(CalculatorContext* cc) override;
+  absl::Status Open(CalculatorContext* cc) final;
+  absl::Status Process(CalculatorContext* cc) final;
 
   int num_output_channels(void) { return num_output_channels_; }
 
@@ -90,8 +90,8 @@ class FramewiseTransformCalculatorBase : public CalculatorBase {
  private:
   // Takes header and options, and sets up state including calling
   // set_num_output_channels() on the base object.
-  virtual mediapipe::Status ConfigureTransform(const TimeSeriesHeader& header,
-                                               CalculatorContext* cc) = 0;
+  virtual absl::Status ConfigureTransform(const TimeSeriesHeader& header,
+                                          CalculatorContext* cc) = 0;
 
   // Takes a vector<double> corresponding to an input frame, and
   // perform the specific transformation to produce an output frame.
@@ -102,23 +102,23 @@ class FramewiseTransformCalculatorBase : public CalculatorBase {
   int num_output_channels_;
 };
 
-mediapipe::Status FramewiseTransformCalculatorBase::Open(
-    CalculatorContext* cc) {
+absl::Status FramewiseTransformCalculatorBase::Open(CalculatorContext* cc) {
   TimeSeriesHeader input_header;
   MP_RETURN_IF_ERROR(time_series_util::FillTimeSeriesHeaderIfValid(
       cc->Inputs().Index(0).Header(), &input_header));
 
-  mediapipe::Status status = ConfigureTransform(input_header, cc);
+  absl::Status status = ConfigureTransform(input_header, cc);
 
   auto output_header = new TimeSeriesHeader(input_header);
   output_header->set_num_channels(num_output_channels_);
   cc->Outputs().Index(0).SetHeader(Adopt(output_header));
 
+  cc->SetOffset(0);
+
   return status;
 }
 
-mediapipe::Status FramewiseTransformCalculatorBase::Process(
-    CalculatorContext* cc) {
+absl::Status FramewiseTransformCalculatorBase::Process(CalculatorContext* cc) {
   const Matrix& input = cc->Inputs().Index(0).Get<Matrix>();
   const int num_frames = input.cols();
   std::unique_ptr<Matrix> output(new Matrix(num_output_channels_, num_frames));
@@ -145,7 +145,7 @@ mediapipe::Status FramewiseTransformCalculatorBase::Process(
   }
   cc->Outputs().Index(0).Add(output.release(), cc->InputTimestamp());
 
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
 // Calculator wrapper around the dsp/mfcc/mfcc.cc routine.
@@ -170,13 +170,13 @@ mediapipe::Status FramewiseTransformCalculatorBase::Process(
 // }
 class MfccCalculator : public FramewiseTransformCalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     return FramewiseTransformCalculatorBase::GetContract(cc);
   }
 
  private:
-  mediapipe::Status ConfigureTransform(const TimeSeriesHeader& header,
-                                       CalculatorContext* cc) override {
+  absl::Status ConfigureTransform(const TimeSeriesHeader& header,
+                                  CalculatorContext* cc) override {
     MfccCalculatorOptions mfcc_options = cc->Options<MfccCalculatorOptions>();
     mfcc_.reset(new audio_dsp::Mfcc());
     int input_length = header.num_channels();
@@ -194,7 +194,7 @@ class MfccCalculator : public FramewiseTransformCalculatorBase {
     // audio_dsp::MelFilterBank needs to know this to
     // correctly interpret the spectrogram bins.
     if (!header.has_audio_sample_rate()) {
-      return mediapipe::InvalidArgumentError(
+      return absl::InvalidArgumentError(
           absl::StrCat("No audio_sample_rate in input TimeSeriesHeader ",
                        PortableDebugString(header)));
     }
@@ -203,10 +203,10 @@ class MfccCalculator : public FramewiseTransformCalculatorBase {
         mfcc_->Initialize(input_length, header.audio_sample_rate());
 
     if (initialized) {
-      return mediapipe::OkStatus();
+      return absl::OkStatus();
     } else {
-      return mediapipe::Status(mediapipe::StatusCode::kInternal,
-                               "Mfcc::Initialize returned uninitialized");
+      return absl::Status(absl::StatusCode::kInternal,
+                          "Mfcc::Initialize returned uninitialized");
     }
   }
 
@@ -228,13 +228,13 @@ REGISTER_CALCULATOR(MfccCalculator);
 // if you ask for too many channels.
 class MelSpectrumCalculator : public FramewiseTransformCalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     return FramewiseTransformCalculatorBase::GetContract(cc);
   }
 
  private:
-  mediapipe::Status ConfigureTransform(const TimeSeriesHeader& header,
-                                       CalculatorContext* cc) override {
+  absl::Status ConfigureTransform(const TimeSeriesHeader& header,
+                                  CalculatorContext* cc) override {
     MelSpectrumCalculatorOptions mel_spectrum_options =
         cc->Options<MelSpectrumCalculatorOptions>();
     mel_filterbank_.reset(new audio_dsp::MelFilterbank());
@@ -245,7 +245,7 @@ class MelSpectrumCalculator : public FramewiseTransformCalculatorBase {
     // audio_dsp::MelFilterBank needs to know this to
     // correctly interpret the spectrogram bins.
     if (!header.has_audio_sample_rate()) {
-      return mediapipe::InvalidArgumentError(
+      return absl::InvalidArgumentError(
           absl::StrCat("No audio_sample_rate in input TimeSeriesHeader ",
                        PortableDebugString(header)));
     }
@@ -255,10 +255,10 @@ class MelSpectrumCalculator : public FramewiseTransformCalculatorBase {
         mel_spectrum_options.max_frequency_hertz());
 
     if (initialized) {
-      return mediapipe::OkStatus();
+      return absl::OkStatus();
     } else {
-      return mediapipe::Status(mediapipe::StatusCode::kInternal,
-                               "mfcc::Initialize returned uninitialized");
+      return absl::Status(absl::StatusCode::kInternal,
+                          "mfcc::Initialize returned uninitialized");
     }
   }
 

mediapipe/calculators/audio/mfcc_mel_calculators_test.cc

@@ -84,7 +84,7 @@ class FramewiseTransformCalculatorTest
     num_samples_per_packet_ = GenerateRandomNonnegInputStream(kNumPackets);
   }
 
-  mediapipe::Status Run() { return this->RunGraph(); }
+  absl::Status Run() { return this->RunGraph(); }
 
   void CheckResults(int expected_num_channels) {
     const auto& output_header =

mediapipe/calculators/audio/rational_factor_resample_calculator.cc

@@ -1,4 +1,4 @@
-// Copyright 2019 The MediaPipe Authors.
+// Copyright 2019, 2021 The MediaPipe Authors.
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -16,22 +16,18 @@
 
 #include "mediapipe/calculators/audio/rational_factor_resample_calculator.h"
 
-#include "audio/dsp/resampler_rational_factor.h"
+#include "audio/dsp/resampler_q.h"
 
-using audio_dsp::DefaultResamplingKernel;
-using audio_dsp::RationalFactorResampler;
 using audio_dsp::Resampler;
 
 namespace mediapipe {
-mediapipe::Status RationalFactorResampleCalculator::Process(
-    CalculatorContext* cc) {
+absl::Status RationalFactorResampleCalculator::Process(CalculatorContext* cc) {
   return ProcessInternal(cc->Inputs().Index(0).Get<Matrix>(), false, cc);
 }
 
-mediapipe::Status RationalFactorResampleCalculator::Close(
-    CalculatorContext* cc) {
+absl::Status RationalFactorResampleCalculator::Close(CalculatorContext* cc) {
   if (initial_timestamp_ == Timestamp::Unstarted()) {
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
   Matrix empty_input_frame(num_channels_, 0);
   return ProcessInternal(empty_input_frame, true, cc);
@@ -40,11 +36,8 @@ mediapipe::Status RationalFactorResampleCalculator::Close(
 namespace {
 void CopyChannelToVector(const Matrix& matrix, int channel,
                          std::vector<float>* vec) {
-  vec->clear();
-  vec->reserve(matrix.cols());
-  for (int sample = 0; sample < matrix.cols(); ++sample) {
-    vec->push_back(matrix(channel, sample));
-  }
+  vec->resize(matrix.cols());
+  Eigen::Map<Eigen::ArrayXf>(vec->data(), vec->size()) = matrix.row(channel);
 }
 
 void CopyVectorToChannel(const std::vector<float>& vec, Matrix* matrix,
@@ -53,17 +46,14 @@ void CopyVectorToChannel(const std::vector<float>& vec, Matrix* matrix,
     matrix->resize(matrix->rows(), vec.size());
   } else {
     CHECK_EQ(vec.size(), matrix->cols());
-    CHECK_LT(channel, matrix->rows());
-  }
-  for (int sample = 0; sample < matrix->cols(); ++sample) {
-    (*matrix)(channel, sample) = vec[sample];
   }
+  CHECK_LT(channel, matrix->rows());
+  matrix->row(channel) =
+      Eigen::Map<const Eigen::ArrayXf>(vec.data(), vec.size());
 }
-
 }  // namespace
 
-mediapipe::Status RationalFactorResampleCalculator::Open(
-    CalculatorContext* cc) {
+absl::Status RationalFactorResampleCalculator::Open(CalculatorContext* cc) {
   RationalFactorResampleCalculatorOptions resample_options =
       cc->Options<RationalFactorResampleCalculatorOptions>();
 
@@ -88,7 +78,7 @@ mediapipe::Status RationalFactorResampleCalculator::Open(
                                resample_options);
       if (!r) {
         LOG(ERROR) << "Failed to initialize resampler.";
-        return mediapipe::UnknownError("Failed to initialize resampler.");
+        return absl::UnknownError("Failed to initialize resampler.");
       }
     }
   }
@@ -106,10 +96,10 @@ mediapipe::Status RationalFactorResampleCalculator::Open(
   initial_timestamp_ = Timestamp::Unstarted();
   check_inconsistent_timestamps_ =
       resample_options.check_inconsistent_timestamps();
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status RationalFactorResampleCalculator::ProcessInternal(
+absl::Status RationalFactorResampleCalculator::ProcessInternal(
     const Matrix& input_frame, bool should_flush, CalculatorContext* cc) {
   if (initial_timestamp_ == Timestamp::Unstarted()) {
     initial_timestamp_ = cc->InputTimestamp();
@@ -131,7 +121,7 @@ mediapipe::Status RationalFactorResampleCalculator::ProcessInternal(
     *output_frame = input_frame;
   } else {
     if (!Resample(input_frame, output_frame.get(), should_flush)) {
-      return mediapipe::UnknownError("Resample() failed.");
+      return absl::UnknownError("Resample() failed.");
     }
   }
   cumulative_output_samples_ += output_frame->cols();
@@ -139,7 +129,7 @@ mediapipe::Status RationalFactorResampleCalculator::ProcessInternal(
   if (output_frame->cols() > 0) {
     cc->Outputs().Index(0).Add(output_frame.release(), output_timestamp);
   }
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
 bool RationalFactorResampleCalculator::Resample(const Matrix& input_frame,
@@ -167,25 +157,28 @@ RationalFactorResampleCalculator::ResamplerFromOptions(
   std::unique_ptr<Resampler<float>> resampler;
   const auto& rational_factor_options =
       options.resampler_rational_factor_options();
-  std::unique_ptr<DefaultResamplingKernel> kernel;
+  audio_dsp::QResamplerParams params;
   if (rational_factor_options.has_radius() &&
       rational_factor_options.has_cutoff() &&
       rational_factor_options.has_kaiser_beta()) {
-    kernel = absl::make_unique<DefaultResamplingKernel>(
-        source_sample_rate, target_sample_rate,
-        rational_factor_options.radius(), rational_factor_options.cutoff(),
-        rational_factor_options.kaiser_beta());
-  } else {
-    kernel = absl::make_unique<DefaultResamplingKernel>(source_sample_rate,
-                                                        target_sample_rate);
+    // Convert RationalFactorResampler kernel parameters to QResampler
+    // settings.
+    params.filter_radius_factor =
+        rational_factor_options.radius() *
+        std::min(1.0, target_sample_rate / source_sample_rate);
+    params.cutoff_proportion = 2 * rational_factor_options.cutoff() /
+                               std::min(source_sample_rate, target_sample_rate);
+    params.kaiser_beta = rational_factor_options.kaiser_beta();
   }
-
   // Set large enough so that the resampling factor between common sample
   // rates (e.g. 8kHz, 16kHz, 22.05kHz, 32kHz, 44.1kHz, 48kHz) is exact, and
   // that any factor is represented with error less than 0.025%.
-  const int kMaxDenominator = 2000;
-  resampler = absl::make_unique<RationalFactorResampler<float>>(
-      *kernel, kMaxDenominator);
+  params.max_denominator = 2000;
+
+  // NOTE: QResampler supports multichannel resampling, so the code might be
+  // simplified using a single instance rather than one per channel.
+  resampler = absl::make_unique<audio_dsp::QResampler<float>>(
+      source_sample_rate, target_sample_rate, /*num_channels=*/1, params);
   if (resampler != nullptr && !resampler->Valid()) {
     resampler = std::unique_ptr<Resampler<float>>();
   }

mediapipe/calculators/audio/rational_factor_resample_calculator.h

@@ -1,4 +1,4 @@
-// Copyright 2019 The MediaPipe Authors.
+// Copyright 2019, 2021 The MediaPipe Authors.
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -36,28 +36,31 @@ namespace mediapipe {
 // stream's sampling rate is specified by target_sample_rate in the
 // RationalFactorResampleCalculatorOptions.  The output time series may have
 // a varying number of samples per frame.
+//
+// NOTE: This calculator uses QResampler, despite the name, which supersedes
+// RationalFactorResampler.
 class RationalFactorResampleCalculator : public CalculatorBase {
  public:
   struct TestAccess;
 
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).Set<Matrix>(
         // Single input stream with TimeSeriesHeader.
     );
     cc->Outputs().Index(0).Set<Matrix>(
         // Resampled stream with TimeSeriesHeader.
     );
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
   // Returns FAIL if the input stream header is invalid or if the
   // resampler cannot be initialized.
-  mediapipe::Status Open(CalculatorContext* cc) override;
+  absl::Status Open(CalculatorContext* cc) override;
   // Resamples a packet of TimeSeries data.  Returns FAIL if the
   // resampler state becomes inconsistent.
-  mediapipe::Status Process(CalculatorContext* cc) override;
+  absl::Status Process(CalculatorContext* cc) override;
   // Flushes any remaining state.  Returns FAIL if the resampler state
   // becomes inconsistent.
-  mediapipe::Status Close(CalculatorContext* cc) override;
+  absl::Status Close(CalculatorContext* cc) override;
 
  protected:
   typedef audio_dsp::Resampler<float> ResamplerType;
@@ -72,8 +75,8 @@ class RationalFactorResampleCalculator : public CalculatorBase {
   // Does Timestamp bookkeeping and resampling common to Process() and
   // Close().  Returns FAIL if the resampler state becomes
   // inconsistent.
-  mediapipe::Status ProcessInternal(const Matrix& input_frame,
-                                    bool should_flush, CalculatorContext* cc);
+  absl::Status ProcessInternal(const Matrix& input_frame, bool should_flush,
+                               CalculatorContext* cc);
 
   // Uses the internal resampler_ objects to actually resample each
   // row of the input TimeSeries.  Returns false if the resampler

mediapipe/calculators/audio/rational_factor_resample_calculator.proto

@@ -1,4 +1,4 @@
-// Copyright 2019 The MediaPipe Authors.
+// Copyright 2019, 2021 The MediaPipe Authors.
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -18,6 +18,8 @@ package mediapipe;
 
 import "mediapipe/framework/calculator.proto";
 
+// NOTE: This calculator uses QResampler, despite the name, which supersedes
+// RationalFactorResampler.
 message RationalFactorResampleCalculatorOptions {
   extend CalculatorOptions {
     optional RationalFactorResampleCalculatorOptions ext = 259760074;
@@ -27,8 +29,7 @@ message RationalFactorResampleCalculatorOptions {
   // stream.  Required.  Must be greater than 0.
   optional double target_sample_rate = 1;
 
-  // Parameters for initializing the RationalFactorResampler. See
-  // RationalFactorResampler for more details.
+  // Parameters for initializing QResampler. See QResampler for more details.
   message ResamplerRationalFactorOptions {
     // Kernel radius in units of input samples.
     optional double radius = 1;

mediapipe/calculators/audio/rational_factor_resample_calculator_test.cc

@@ -80,7 +80,7 @@ class RationalFactorResampleCalculatorTest
   }
 
   // Initializes and runs the test graph.
-  mediapipe::Status Run(double output_sample_rate) {
+  absl::Status Run(double output_sample_rate) {
     options_.set_target_sample_rate(output_sample_rate);
     InitializeGraph();
 
@@ -120,7 +120,6 @@ class RationalFactorResampleCalculatorTest
 
     // The exact number of expected samples may vary based on the implementation
     // of the resampler since the exact value is not an integer.
-    // TODO: Reduce this offset to + 1 once cl/185829520 is submitted.
     const double expected_num_output_samples = num_input_samples_ * factor;
     EXPECT_LE(ceil(expected_num_output_samples), num_output_samples);
     EXPECT_GE(ceil(expected_num_output_samples) + 11, num_output_samples);

mediapipe/calculators/audio/spectrogram_calculator.cc

@@ -66,7 +66,7 @@ namespace mediapipe {
 // analysis frame will advance from its predecessor by the same time step.
 class SpectrogramCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).Set<Matrix>(
         // Input stream with TimeSeriesHeader.
     );
@@ -96,26 +96,34 @@ class SpectrogramCalculator : public CalculatorBase {
         );
       }
     }
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   // Returns FAIL if the input stream header is invalid.
-  mediapipe::Status Open(CalculatorContext* cc) override;
+  absl::Status Open(CalculatorContext* cc) override;
 
   // Outputs at most one packet consisting of a single Matrix with one or
   // more columns containing the spectral values from as many input frames
   // as are completed by the input samples.  Always returns OK.
-  mediapipe::Status Process(CalculatorContext* cc) override;
+  absl::Status Process(CalculatorContext* cc) override;
 
   // Performs zero-padding and processing of any remaining samples
   // if pad_final_packet is set.
   // Returns OK.
-  mediapipe::Status Close(CalculatorContext* cc) override;
+  absl::Status Close(CalculatorContext* cc) override;
 
  private:
   Timestamp CurrentOutputTimestamp(CalculatorContext* cc) {
     if (use_local_timestamp_) {
-      return cc->InputTimestamp();
+      const Timestamp now = cc->InputTimestamp();
+      if (now == Timestamp::Done()) {
+        // During Close the timestamp is not available, send an estimate.
+        return last_local_output_timestamp_ +
+               round(last_completed_frames_ * frame_step_samples() *
+                     Timestamp::kTimestampUnitsPerSecond / input_sample_rate_);
+      }
+      last_local_output_timestamp_ = now;
+      return now;
     }
     return CumulativeOutputTimestamp();
   }
@@ -138,17 +146,20 @@ class SpectrogramCalculator : public CalculatorBase {
   // Convert the output of the spectrogram object into a Matrix (or an
   // Eigen::MatrixXcf if complex-valued output is requested) and pass to
   // MediaPipe output.
-  mediapipe::Status ProcessVector(const Matrix& input_stream,
-                                  CalculatorContext* cc);
+  absl::Status ProcessVector(const Matrix& input_stream, CalculatorContext* cc);
 
   // Templated function to process either real- or complex-output spectrogram.
   template <class OutputMatrixType>
-  mediapipe::Status ProcessVectorToOutput(
+  absl::Status ProcessVectorToOutput(
       const Matrix& input_stream,
       const OutputMatrixType postprocess_output_fn(const OutputMatrixType&),
       CalculatorContext* cc);
 
+  // Use the MediaPipe timestamp instead of the estimated one. Useful when the
+  // data is intermittent.
   bool use_local_timestamp_;
+  Timestamp last_local_output_timestamp_;
+
   double input_sample_rate_;
   bool pad_final_packet_;
   int frame_duration_samples_;
@@ -157,6 +168,9 @@ class SpectrogramCalculator : public CalculatorBase {
   int64 cumulative_input_samples_;
   // How many frames we've emitted, used for calculating output time stamps.
   int64 cumulative_completed_frames_;
+  // How many frames were emitted last, used for estimating the timestamp on
+  // Close when use_local_timestamp_ is true;
+  int64 last_completed_frames_;
   Timestamp initial_input_timestamp_;
   int num_input_channels_;
   // How many frequency bins we emit (=N_FFT/2 + 1).
@@ -177,7 +191,7 @@ REGISTER_CALCULATOR(SpectrogramCalculator);
 // Factor to convert ln(magnitude_squared) to deciBels = 10.0/ln(10.0).
 const float SpectrogramCalculator::kLnPowerToDb = 4.342944819032518;
 
-mediapipe::Status SpectrogramCalculator::Open(CalculatorContext* cc) {
+absl::Status SpectrogramCalculator::Open(CalculatorContext* cc) {
   SpectrogramCalculatorOptions spectrogram_options =
       cc->Options<SpectrogramCalculatorOptions>();
 
@@ -271,11 +285,20 @@ mediapipe::Status SpectrogramCalculator::Open(CalculatorContext* cc) {
         Adopt(multichannel_output_header.release()));
   }
   cumulative_completed_frames_ = 0;
+  last_completed_frames_ = 0;
   initial_input_timestamp_ = Timestamp::Unstarted();
-  return mediapipe::OkStatus();
+  if (use_local_timestamp_) {
+    // Inform the framework that the calculator will output packets at the same
+    // timestamps as input packets to enable packet queueing optimizations. The
+    // final packet (emitted from Close()) does not follow this rule but it's
+    // sufficient that its timestamp is strictly greater than the timestamp of
+    // the previous packet.
+    cc->SetOffset(0);
+  }
+  return absl::OkStatus();
 }
 
-mediapipe::Status SpectrogramCalculator::Process(CalculatorContext* cc) {
+absl::Status SpectrogramCalculator::Process(CalculatorContext* cc) {
   if (initial_input_timestamp_ == Timestamp::Unstarted()) {
     initial_input_timestamp_ = cc->InputTimestamp();
   }
@@ -291,7 +314,7 @@ mediapipe::Status SpectrogramCalculator::Process(CalculatorContext* cc) {
 }
 
 template <class OutputMatrixType>
-mediapipe::Status SpectrogramCalculator::ProcessVectorToOutput(
+absl::Status SpectrogramCalculator::ProcessVectorToOutput(
     const Matrix& input_stream,
     const OutputMatrixType postprocess_output_fn(const OutputMatrixType&),
     CalculatorContext* cc) {
@@ -311,8 +334,8 @@ mediapipe::Status SpectrogramCalculator::ProcessVectorToOutput(
 
     if (!spectrogram_generators_[channel]->ComputeSpectrogram(
             input_vector, &output_vectors)) {
-      return mediapipe::Status(mediapipe::StatusCode::kInternal,
-                               "Spectrogram returned failure");
+      return absl::Status(absl::StatusCode::kInternal,
+                          "Spectrogram returned failure");
     }
     if (channel == 0) {
       // Record the number of time frames we expect from each channel.
@@ -354,12 +377,19 @@ mediapipe::Status SpectrogramCalculator::ProcessVectorToOutput(
           CurrentOutputTimestamp(cc));
     }
     cumulative_completed_frames_ += output_vectors.size();
+    last_completed_frames_ = output_vectors.size();
+    if (!use_local_timestamp_) {
+      // In non-local timestamp mode the timestamp of the next packet will be
+      // equal to CumulativeOutputTimestamp(). Inform the framework about this
+      // fact to enable packet queueing optimizations.
+      cc->Outputs().Index(0).SetNextTimestampBound(CumulativeOutputTimestamp());
+    }
   }
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status SpectrogramCalculator::ProcessVector(
-    const Matrix& input_stream, CalculatorContext* cc) {
+absl::Status SpectrogramCalculator::ProcessVector(const Matrix& input_stream,
+                                                  CalculatorContext* cc) {
   switch (output_type_) {
     // These blocks deliberately ignore clang-format to preserve the
     // "silhouette" of the different cases.
@@ -394,13 +424,13 @@ mediapipe::Status SpectrogramCalculator::ProcessVector(
     }
     // clang-format on
     default: {
-      return mediapipe::Status(mediapipe::StatusCode::kInvalidArgument,
-                               "Unrecognized spectrogram output type.");
+      return absl::Status(absl::StatusCode::kInvalidArgument,
+                          "Unrecognized spectrogram output type.");
     }
   }
 }
 
-mediapipe::Status SpectrogramCalculator::Close(CalculatorContext* cc) {
+absl::Status SpectrogramCalculator::Close(CalculatorContext* cc) {
   if (cumulative_input_samples_ > 0 && pad_final_packet_) {
     // We can flush any remaining samples by sending frame_step_samples - 1
     // zeros to the Process method, and letting it do its thing,
@@ -416,7 +446,7 @@ mediapipe::Status SpectrogramCalculator::Close(CalculatorContext* cc) {
         Matrix::Zero(num_input_channels_, required_padding_samples), cc);
   }
 
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
 }  // namespace mediapipe

mediapipe/calculators/audio/spectrogram_calculator_test.cc

@@ -50,7 +50,7 @@ class SpectrogramCalculatorTest
   }
 
   // Initializes and runs the test graph.
-  mediapipe::Status Run() {
+  absl::Status Run() {
     // Now that options are set, we can set up some internal constants.
     frame_duration_samples_ =
         round(options_.frame_duration_seconds() * input_sample_rate_);

mediapipe/calculators/audio/stabilized_log_calculator.cc

@@ -41,17 +41,17 @@ namespace mediapipe {
 // }
 class StabilizedLogCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).Set<Matrix>(
         // Input stream with TimeSeriesHeader.
     );
     cc->Outputs().Index(0).Set<Matrix>(
         // Output stabilized log stream with TimeSeriesHeader.
     );
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override {
+  absl::Status Open(CalculatorContext* cc) override {
     StabilizedLogCalculatorOptions stabilized_log_calculator_options =
         cc->Options<StabilizedLogCalculatorOptions>();
 
@@ -70,23 +70,23 @@ class StabilizedLogCalculator : public CalculatorBase {
       cc->Outputs().Index(0).SetHeader(
           Adopt(new TimeSeriesHeader(input_header)));
     }
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) override {
+  absl::Status Process(CalculatorContext* cc) override {
     auto input_matrix = cc->Inputs().Index(0).Get<Matrix>();
     if (input_matrix.array().isNaN().any()) {
-      return mediapipe::InvalidArgumentError("NaN input to log operation.");
+      return absl::InvalidArgumentError("NaN input to log operation.");
     }
     if (check_nonnegativity_) {
       if (input_matrix.minCoeff() < 0.0) {
-        return mediapipe::OutOfRangeError("Negative input to log operation.");
+        return absl::OutOfRangeError("Negative input to log operation.");
       }
     }
     std::unique_ptr<Matrix> output_frame(new Matrix(
         output_scale_ * (input_matrix.array() + stabilizer_).log().matrix()));
     cc->Outputs().Index(0).Add(output_frame.release(), cc->InputTimestamp());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
  private:

mediapipe/calculators/audio/time_series_framer_calculator.cc

@@ -66,26 +66,26 @@ namespace mediapipe {
 // cumulative_completed_samples / sample_rate_.
 class TimeSeriesFramerCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).Set<Matrix>(
         // Input stream with TimeSeriesHeader.
     );
     cc->Outputs().Index(0).Set<Matrix>(
         // Fixed length time series Packets with TimeSeriesHeader.
     );
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   // Returns FAIL if the input stream header is invalid.
-  mediapipe::Status Open(CalculatorContext* cc) override;
+  absl::Status Open(CalculatorContext* cc) override;
 
   // Outputs as many framed packets as possible given the accumulated
   // input.  Always returns OK.
-  mediapipe::Status Process(CalculatorContext* cc) override;
+  absl::Status Process(CalculatorContext* cc) override;
 
   // Flushes any remaining samples in a zero-padded packet.  Always
   // returns OK.
-  mediapipe::Status Close(CalculatorContext* cc) override;
+  absl::Status Close(CalculatorContext* cc) override;
 
  private:
   // Adds input data to the internal buffer.
@@ -134,7 +134,6 @@ class TimeSeriesFramerCalculator : public CalculatorBase {
   // emulate_fractional_frame_overlap is true.
   double average_frame_step_samples_;
   int samples_still_to_drop_;
-  int64 cumulative_input_samples_;
   int64 cumulative_output_frames_;
   // "Completed" samples are samples that are no longer needed because
   // the framer has completely stepped past them (taking into account
@@ -163,8 +162,6 @@ void TimeSeriesFramerCalculator::EnqueueInput(CalculatorContext* cc) {
     sample_buffer_.emplace_back(std::make_pair(
         input_frame.col(i), CurrentSampleTimestamp(cc->InputTimestamp(), i)));
   }
-
-  cumulative_input_samples_ += input_frame.cols();
 }
 
 void TimeSeriesFramerCalculator::FrameOutput(CalculatorContext* cc) {
@@ -203,9 +200,15 @@ void TimeSeriesFramerCalculator::FrameOutput(CalculatorContext* cc) {
     ++cumulative_output_frames_;
     cumulative_completed_samples_ += frame_step_samples;
   }
+  if (!use_local_timestamp_) {
+    // In non-local timestamp mode the timestamp of the next packet will be
+    // equal to CumulativeOutputTimestamp(). Inform the framework about this
+    // fact to enable packet queueing optimizations.
+    cc->Outputs().Index(0).SetNextTimestampBound(CumulativeOutputTimestamp());
+  }
 }
 
-mediapipe::Status TimeSeriesFramerCalculator::Process(CalculatorContext* cc) {
+absl::Status TimeSeriesFramerCalculator::Process(CalculatorContext* cc) {
   if (initial_input_timestamp_ == Timestamp::Unstarted()) {
     initial_input_timestamp_ = cc->InputTimestamp();
     current_timestamp_ = initial_input_timestamp_;
@@ -214,10 +217,10 @@ mediapipe::Status TimeSeriesFramerCalculator::Process(CalculatorContext* cc) {
   EnqueueInput(cc);
   FrameOutput(cc);
 
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status TimeSeriesFramerCalculator::Close(CalculatorContext* cc) {
+absl::Status TimeSeriesFramerCalculator::Close(CalculatorContext* cc) {
   while (samples_still_to_drop_ > 0 && !sample_buffer_.empty()) {
     sample_buffer_.pop_front();
     --samples_still_to_drop_;
@@ -234,10 +237,10 @@ mediapipe::Status TimeSeriesFramerCalculator::Close(CalculatorContext* cc) {
                                CurrentOutputTimestamp());
   }
 
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
-mediapipe::Status TimeSeriesFramerCalculator::Open(CalculatorContext* cc) {
+absl::Status TimeSeriesFramerCalculator::Open(CalculatorContext* cc) {
   TimeSeriesFramerCalculatorOptions framer_options =
       cc->Options<TimeSeriesFramerCalculatorOptions>();
 
@@ -286,7 +289,6 @@ mediapipe::Status TimeSeriesFramerCalculator::Open(CalculatorContext* cc) {
   }
   cc->Outputs().Index(0).SetHeader(Adopt(output_header));
   cumulative_completed_samples_ = 0;
-  cumulative_input_samples_ = 0;
   cumulative_output_frames_ = 0;
   samples_still_to_drop_ = 0;
   initial_input_timestamp_ = Timestamp::Unstarted();
@@ -317,7 +319,7 @@ mediapipe::Status TimeSeriesFramerCalculator::Open(CalculatorContext* cc) {
   }
   use_local_timestamp_ = framer_options.use_local_timestamp();
 
-  return mediapipe::OkStatus();
+  return absl::OkStatus();
 }
 
 }  // namespace mediapipe

mediapipe/calculators/audio/time_series_framer_calculator_test.cc

@@ -69,7 +69,7 @@ class TimeSeriesFramerCalculatorTest
   }
 
   // Initializes and runs the test graph.
-  mediapipe::Status Run() {
+  absl::Status Run() {
     InitializeGraph();
 
     FillInputHeader();
@@ -441,7 +441,7 @@ class TimeSeriesFramerCalculatorTimestampingTest
     }
   }
 
-  mediapipe::Status RunTimestampTest() {
+  absl::Status RunTimestampTest() {
     InitializeGraph();
     InitializeInputForTimeStampingTest();
     FillInputHeader();

mediapipe/calculators/core/BUILD

@@ -140,12 +140,23 @@ mediapipe_proto_library(
     ],
 )
 
+mediapipe_proto_library(
+    name = "graph_profile_calculator_proto",
+    srcs = ["graph_profile_calculator.proto"],
+    visibility = ["//visibility:public"],
+    deps = [
+        "//mediapipe/framework:calculator_options_proto",
+        "//mediapipe/framework:calculator_proto",
+    ],
+)
+
 cc_library(
     name = "add_header_calculator",
     srcs = ["add_header_calculator.cc"],
     visibility = ["//visibility:public"],
     deps = [
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/port:logging",
         "//mediapipe/framework/port:status",
     ],
@@ -232,6 +243,22 @@ cc_test(
     ],
 )
 
+cc_library(
+    name = "concatenate_vector_calculator_hdr",
+    hdrs = ["concatenate_vector_calculator.h"],
+    visibility = ["//visibility:public"],
+    deps = [
+        ":concatenate_vector_calculator_cc_proto",
+        "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
+        "//mediapipe/framework/api2:port",
+        "//mediapipe/framework/port:integral_types",
+        "//mediapipe/framework/port:ret_check",
+        "//mediapipe/framework/port:status",
+    ],
+    alwayslink = 1,
+)
+
 cc_library(
     name = "concatenate_vector_calculator",
     srcs = ["concatenate_vector_calculator.cc"],
@@ -248,6 +275,8 @@ cc_library(
     visibility = ["//visibility:public"],
     deps = [
         ":concatenate_vector_calculator_cc_proto",
+        "//mediapipe/framework/api2:node",
+        "//mediapipe/framework/api2:port",
         "//mediapipe/framework/formats:classification_cc_proto",
         "//mediapipe/framework/formats:landmark_cc_proto",
         "//mediapipe/framework/formats:tensor",
@@ -286,6 +315,7 @@ cc_library(
     deps = [
         ":concatenate_vector_calculator_cc_proto",
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/formats:landmark_cc_proto",
         "//mediapipe/framework/port:ret_check",
         "//mediapipe/framework/port:status",
@@ -393,11 +423,29 @@ cc_library(
     ],
     deps = [
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/port:status",
     ],
     alwayslink = 1,
 )
 
+cc_test(
+    name = "make_pair_calculator_test",
+    size = "small",
+    srcs = ["make_pair_calculator_test.cc"],
+    deps = [
+        ":make_pair_calculator",
+        "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework:calculator_runner",
+        "//mediapipe/framework:timestamp",
+        "//mediapipe/framework/port:gtest_main",
+        "//mediapipe/framework/port:status",
+        "//mediapipe/framework/tool:validate_type",
+        "//mediapipe/util:packet_test_util",
+        "//mediapipe/util:time_series_test_util",
+    ],
+)
+
 cc_library(
     name = "matrix_multiply_calculator",
     srcs = ["matrix_multiply_calculator.cc"],
@@ -406,10 +454,10 @@ cc_library(
     ],
     deps = [
         "//mediapipe/framework:calculator_framework",
-        "//mediapipe/framework:timestamp",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/formats:matrix",
         "//mediapipe/framework/port:status",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -422,10 +470,10 @@ cc_library(
     ],
     deps = [
         "//mediapipe/framework:calculator_framework",
-        "//mediapipe/framework:timestamp",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/formats:matrix",
         "//mediapipe/framework/port:status",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -438,12 +486,42 @@ cc_library(
     ],
     deps = [
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/port:ret_check",
         "//mediapipe/framework/stream_handler:mux_input_stream_handler",
     ],
     alwayslink = 1,
 )
 
+cc_library(
+    name = "non_zero_calculator",
+    srcs = ["non_zero_calculator.cc"],
+    visibility = [
+        "//visibility:public",
+    ],
+    deps = [
+        "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
+        "//mediapipe/framework/port:ret_check",
+    ],
+    alwayslink = 1,
+)
+
+cc_test(
+    name = "non_zero_calculator_test",
+    size = "small",
+    srcs = ["non_zero_calculator_test.cc"],
+    deps = [
+        ":non_zero_calculator",
+        "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework:calculator_runner",
+        "//mediapipe/framework:timestamp",
+        "//mediapipe/framework/port:gtest_main",
+        "//mediapipe/framework/port:status",
+        "//mediapipe/framework/tool:validate_type",
+    ],
+)
+
 cc_test(
     name = "mux_calculator_test",
     srcs = ["mux_calculator_test.cc"],
@@ -550,6 +628,7 @@ cc_library(
     ],
     deps = [
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/port:ret_check",
     ],
     alwayslink = 1,
@@ -606,6 +685,7 @@ cc_library(
         "//mediapipe/framework:calculator_framework",
         "//mediapipe/framework:packet",
         "//mediapipe/framework:timestamp",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/port:ret_check",
         "//mediapipe/framework/port:status",
         "//mediapipe/framework/stream_handler:immediate_input_stream_handler",
@@ -643,6 +723,18 @@ cc_library(
     alwayslink = 1,
 )
 
+cc_library(
+    name = "default_side_packet_calculator",
+    srcs = ["default_side_packet_calculator.cc"],
+    visibility = ["//visibility:public"],
+    deps = [
+        "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/port:ret_check",
+        "//mediapipe/framework/port:status",
+    ],
+    alwayslink = 1,
+)
+
 cc_library(
     name = "side_packet_to_stream_calculator",
     srcs = ["side_packet_to_stream_calculator.cc"],
@@ -768,7 +860,7 @@ cc_test(
         "//mediapipe/framework/port:gtest_main",
         "//mediapipe/framework/port:logging",
         "//mediapipe/framework/tool:validate_type",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )
 
@@ -785,7 +877,7 @@ cc_test(
         "//mediapipe/framework/port:logging",
         "//mediapipe/framework/port:parse_text_proto",
         "//mediapipe/framework/tool:validate_type",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
 )
 
@@ -868,8 +960,8 @@ cc_test(
 )
 
 cc_library(
-    name = "split_normalized_landmark_list_calculator",
-    srcs = ["split_normalized_landmark_list_calculator.cc"],
+    name = "split_landmarks_calculator",
+    srcs = ["split_landmarks_calculator.cc"],
     visibility = ["//visibility:public"],
     deps = [
         ":split_vector_calculator_cc_proto",
@@ -883,10 +975,10 @@ cc_library(
 )
 
 cc_test(
-    name = "split_normalized_landmark_list_calculator_test",
-    srcs = ["split_normalized_landmark_list_calculator_test.cc"],
+    name = "split_landmarks_calculator_test",
+    srcs = ["split_landmarks_calculator_test.cc"],
     deps = [
-        ":split_normalized_landmark_list_calculator",
+        ":split_landmarks_calculator",
         ":split_vector_calculator_cc_proto",
         "//mediapipe/framework:calculator_framework",
         "//mediapipe/framework:calculator_runner",
@@ -958,6 +1050,7 @@ cc_library(
     deps = [
         ":sequence_shift_calculator_cc_proto",
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/port:status",
     ],
     alwayslink = 1,
@@ -1007,6 +1100,7 @@ cc_library(
     visibility = ["//visibility:public"],
     deps = [
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/formats:matrix",
         "//mediapipe/framework/port:integral_types",
         "//mediapipe/framework/port:logging",
@@ -1014,7 +1108,7 @@ cc_library(
         "//mediapipe/framework/tool:status_util",
         "//mediapipe/util:time_series_util",
         "@com_google_absl//absl/memory",
-        "@eigen_archive//:eigen",
+        "@eigen_archive//:eigen3",
     ],
     alwayslink = 1,
 )
@@ -1042,6 +1136,7 @@ cc_library(
     visibility = ["//visibility:public"],
     deps = [
         "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework/api2:node",
         "//mediapipe/framework/port:ret_check",
         "//mediapipe/framework/port:status",
     ],
@@ -1115,3 +1210,45 @@ cc_test(
         "@com_google_absl//absl/strings",
     ],
 )
+
+cc_library(
+    name = "graph_profile_calculator",
+    srcs = ["graph_profile_calculator.cc"],
+    visibility = ["//visibility:public"],
+    deps = [
+        ":graph_profile_calculator_cc_proto",
+        "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework:calculator_profile_cc_proto",
+        "//mediapipe/framework/api2:node",
+        "//mediapipe/framework/api2:packet",
+        "//mediapipe/framework/api2:port",
+        "//mediapipe/framework/port:ret_check",
+        "//mediapipe/framework/port:status",
+    ],
+    alwayslink = 1,
+)
+
+cc_test(
+    name = "graph_profile_calculator_test",
+    srcs = ["graph_profile_calculator_test.cc"],
+    deps = [
+        ":graph_profile_calculator",
+        "//mediapipe/framework:calculator_cc_proto",
+        "//mediapipe/framework:calculator_framework",
+        "//mediapipe/framework:calculator_profile_cc_proto",
+        "//mediapipe/framework:test_calculators",
+        "//mediapipe/framework/deps:clock",
+        "//mediapipe/framework/deps:message_matchers",
+        "//mediapipe/framework/port:core_proto",
+        "//mediapipe/framework/port:gtest_main",
+        "//mediapipe/framework/port:integral_types",
+        "//mediapipe/framework/port:logging",
+        "//mediapipe/framework/port:parse_text_proto",
+        "//mediapipe/framework/port:threadpool",
+        "//mediapipe/framework/tool:simulation_clock_executor",
+        "//mediapipe/framework/tool:sink",
+        "@com_google_absl//absl/status",
+        "@com_google_absl//absl/strings",
+        "@com_google_absl//absl/time",
+    ],
+)

mediapipe/calculators/core/add_header_calculator.cc

@@ -12,11 +12,13 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+#include "mediapipe/framework/api2/node.h"
 #include "mediapipe/framework/calculator_framework.h"
 #include "mediapipe/framework/port/canonical_errors.h"
 #include "mediapipe/framework/port/logging.h"
 
 namespace mediapipe {
+namespace api2 {
 
 // Attach the header from a stream or side input to another stream.
 //
@@ -42,49 +44,41 @@ namespace mediapipe {
 //   output_stream: "audio_with_header"
 // }
 //
-class AddHeaderCalculator : public CalculatorBase {
+class AddHeaderCalculator : public Node {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
-    bool has_side_input = false;
-    bool has_header_stream = false;
-    if (cc->InputSidePackets().HasTag("HEADER")) {
-      cc->InputSidePackets().Tag("HEADER").SetAny();
-      has_side_input = true;
-    }
-    if (cc->Inputs().HasTag("HEADER")) {
-      cc->Inputs().Tag("HEADER").SetNone();
-      has_header_stream = true;
-    }
-    if (has_side_input == has_header_stream) {
-      return mediapipe::InvalidArgumentError(
+  static constexpr Input<NoneType>::Optional kHeader{"HEADER"};
+  static constexpr SideInput<AnyType>::Optional kHeaderSide{"HEADER"};
+  static constexpr Input<AnyType> kData{"DATA"};
+  static constexpr Output<SameType<kData>> kOut{""};
+
+  MEDIAPIPE_NODE_CONTRACT(kHeader, kHeaderSide, kData, kOut);
+
+  static absl::Status UpdateContract(CalculatorContract* cc) {
+    if (kHeader(cc).IsConnected() == kHeaderSide(cc).IsConnected()) {
+      return absl::InvalidArgumentError(
           "Header must be provided via exactly one of side input and input "
           "stream");
     }
-    cc->Inputs().Tag("DATA").SetAny();
-    cc->Outputs().Index(0).SetSameAs(&cc->Inputs().Tag("DATA"));
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override {
-    Packet header;
-    if (cc->InputSidePackets().HasTag("HEADER")) {
-      header = cc->InputSidePackets().Tag("HEADER");
-    }
-    if (cc->Inputs().HasTag("HEADER")) {
-      header = cc->Inputs().Tag("HEADER").Header();
-    }
+  absl::Status Open(CalculatorContext* cc) override {
+    const PacketBase& header =
+        kHeader(cc).IsConnected() ? kHeader(cc).Header() : kHeaderSide(cc);
     if (!header.IsEmpty()) {
-      cc->Outputs().Index(0).SetHeader(header);
+      kOut(cc).SetHeader(header);
     }
-    cc->SetOffset(TimestampDiff(0));
-    return mediapipe::OkStatus();
+    cc->SetOffset(0);
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) override {
-    cc->Outputs().Index(0).AddPacket(cc->Inputs().Tag("DATA").Value());
-    return mediapipe::OkStatus();
+  absl::Status Process(CalculatorContext* cc) override {
+    kOut(cc).Send(kData(cc).packet());
+    return absl::OkStatus();
   }
 };
 
-REGISTER_CALCULATOR(AddHeaderCalculator);
+MEDIAPIPE_REGISTER_NODE(AddHeaderCalculator);
+
+}  // namespace api2
 }  // namespace mediapipe

mediapipe/calculators/core/add_header_calculator_test.cc

@@ -24,6 +24,9 @@
 
 namespace mediapipe {
 
+constexpr char kDataTag[] = "DATA";
+constexpr char kHeaderTag[] = "HEADER";
+
 class AddHeaderCalculatorTest : public ::testing::Test {};
 
 TEST_F(AddHeaderCalculatorTest, HeaderStream) {
@@ -36,11 +39,11 @@ TEST_F(AddHeaderCalculatorTest, HeaderStream) {
   CalculatorRunner runner(node);
 
   // Set header and add 5 packets.
-  runner.MutableInputs()->Tag("HEADER").header =
+  runner.MutableInputs()->Tag(kHeaderTag).header =
       Adopt(new std::string("my_header"));
   for (int i = 0; i < 5; ++i) {
     Packet packet = Adopt(new int(i)).At(Timestamp(i * 1000));
-    runner.MutableInputs()->Tag("DATA").packets.push_back(packet);
+    runner.MutableInputs()->Tag(kDataTag).packets.push_back(packet);
   }
 
   // Run calculator.
@@ -85,13 +88,14 @@ TEST_F(AddHeaderCalculatorTest, NoPacketsOnHeaderStream) {
   CalculatorRunner runner(node);
 
   // Set header and add 5 packets.
-  runner.MutableInputs()->Tag("HEADER").header =
+  runner.MutableInputs()->Tag(kHeaderTag).header =
       Adopt(new std::string("my_header"));
-  runner.MutableInputs()->Tag("HEADER").packets.push_back(
-      Adopt(new std::string("not allowed")));
+  runner.MutableInputs()
+      ->Tag(kHeaderTag)
+      .packets.push_back(Adopt(new std::string("not allowed")));
   for (int i = 0; i < 5; ++i) {
     Packet packet = Adopt(new int(i)).At(Timestamp(i * 1000));
-    runner.MutableInputs()->Tag("DATA").packets.push_back(packet);
+    runner.MutableInputs()->Tag(kDataTag).packets.push_back(packet);
   }
 
   // Run calculator.
@@ -108,11 +112,11 @@ TEST_F(AddHeaderCalculatorTest, InputSidePacket) {
   CalculatorRunner runner(node);
 
   // Set header and add 5 packets.
-  runner.MutableSidePackets()->Tag("HEADER") =
+  runner.MutableSidePackets()->Tag(kHeaderTag) =
       Adopt(new std::string("my_header"));
   for (int i = 0; i < 5; ++i) {
     Packet packet = Adopt(new int(i)).At(Timestamp(i * 1000));
-    runner.MutableInputs()->Tag("DATA").packets.push_back(packet);
+    runner.MutableInputs()->Tag(kDataTag).packets.push_back(packet);
   }
 
   // Run calculator.
@@ -143,17 +147,17 @@ TEST_F(AddHeaderCalculatorTest, UsingBothSideInputAndStream) {
   CalculatorRunner runner(node);
 
   // Set both headers and add 5 packets.
-  runner.MutableSidePackets()->Tag("HEADER") =
+  runner.MutableSidePackets()->Tag(kHeaderTag) =
       Adopt(new std::string("my_header"));
-  runner.MutableSidePackets()->Tag("HEADER") =
+  runner.MutableSidePackets()->Tag(kHeaderTag) =
       Adopt(new std::string("my_header"));
   for (int i = 0; i < 5; ++i) {
     Packet packet = Adopt(new int(i)).At(Timestamp(i * 1000));
-    runner.MutableInputs()->Tag("DATA").packets.push_back(packet);
+    runner.MutableInputs()->Tag(kDataTag).packets.push_back(packet);
   }
 
   // Run should fail because header can only be provided one way.
-  EXPECT_EQ(runner.Run().code(), mediapipe::InvalidArgumentError("").code());
+  EXPECT_EQ(runner.Run().code(), absl::InvalidArgumentError("").code());
 }
 
 }  // namespace mediapipe

mediapipe/calculators/core/begin_end_loop_calculator_graph_test.cc

@@ -42,22 +42,22 @@ REGISTER_CALCULATOR(BeginLoopIntegerCalculator);
 
 class IncrementCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).Set<int>();
     cc->Outputs().Index(0).Set<int>();
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override {
+  absl::Status Open(CalculatorContext* cc) override {
     cc->SetOffset(TimestampDiff(0));
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) override {
+  absl::Status Process(CalculatorContext* cc) override {
     const int& input_int = cc->Inputs().Index(0).Get<int>();
     auto output_int = absl::make_unique<int>(input_int + 1);
     cc->Outputs().Index(0).Add(output_int.release(), cc->InputTimestamp());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 };
 
@@ -70,7 +70,7 @@ class BeginEndLoopCalculatorGraphTest : public ::testing::Test {
  protected:
   void SetUp() override {
     auto graph_config = ParseTextProtoOrDie<CalculatorGraphConfig>(
-        R"(
+        R"pb(
           num_threads: 4
           input_stream: "ints"
           node {
@@ -90,7 +90,7 @@ class BeginEndLoopCalculatorGraphTest : public ::testing::Test {
             input_stream: "BATCH_END:timestamp"
             output_stream: "ITERABLE:ints_plus_one"
           }
-        )");
+        )pb");
     tool::AddVectorSink("ints_plus_one", &graph_config, &output_packets_);
     MP_ASSERT_OK(graph_.Initialize(graph_config));
     MP_ASSERT_OK(graph_.StartRun({}));
@@ -166,19 +166,19 @@ TEST_F(BeginEndLoopCalculatorGraphTest, MultipleVectors) {
 // bound update.
 class PassThroughOrEmptyVectorCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->SetProcessTimestampBounds(true);
     cc->Inputs().Index(0).Set<std::vector<int>>();
     cc->Outputs().Index(0).Set<std::vector<int>>();
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override {
+  absl::Status Open(CalculatorContext* cc) override {
     cc->SetOffset(TimestampDiff(0));
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) override {
+  absl::Status Process(CalculatorContext* cc) override {
     if (!cc->Inputs().Index(0).IsEmpty()) {
       cc->Outputs().Index(0).AddPacket(cc->Inputs().Index(0).Value());
     } else {
@@ -186,7 +186,7 @@ class PassThroughOrEmptyVectorCalculator : public CalculatorBase {
           MakePacket<std::vector<int>>(std::vector<int>())
               .At(cc->InputTimestamp()));
     }
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 };
 
@@ -197,7 +197,7 @@ class BeginEndLoopCalculatorGraphProcessingEmptyPacketsTest
  protected:
   void SetUp() override {
     auto graph_config = ParseTextProtoOrDie<CalculatorGraphConfig>(
-        R"(
+        R"pb(
           num_threads: 4
           input_stream: "ints"
           input_stream: "force_ints_to_be_timestamp_bound_update"
@@ -229,7 +229,7 @@ class BeginEndLoopCalculatorGraphProcessingEmptyPacketsTest
             input_stream: "ints_plus_one"
             output_stream: "ints_plus_one_passed_through"
           }
-        )");
+        )pb");
     tool::AddVectorSink("ints_plus_one_passed_through", &graph_config,
                         &output_packets_);
     MP_ASSERT_OK(graph_.Initialize(graph_config));
@@ -311,24 +311,24 @@ TEST_F(BeginEndLoopCalculatorGraphProcessingEmptyPacketsTest, MultipleVectors) {
 
 class MultiplierCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     cc->Inputs().Index(0).Set<int>();
     cc->Inputs().Index(1).Set<int>();
     cc->Outputs().Index(0).Set<int>();
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override {
+  absl::Status Open(CalculatorContext* cc) override {
     cc->SetOffset(TimestampDiff(0));
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) override {
+  absl::Status Process(CalculatorContext* cc) override {
     const int& input_int = cc->Inputs().Index(0).Get<int>();
     const int& multiplier_int = cc->Inputs().Index(1).Get<int>();
     auto output_int = absl::make_unique<int>(input_int * multiplier_int);
     cc->Outputs().Index(0).Add(output_int.release(), cc->InputTimestamp());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 };
 
@@ -338,7 +338,7 @@ class BeginEndLoopCalculatorGraphWithClonedInputsTest : public ::testing::Test {
  protected:
   void SetUp() override {
     auto graph_config = ParseTextProtoOrDie<CalculatorGraphConfig>(
-        R"(
+        R"pb(
           num_threads: 4
           input_stream: "ints"
           input_stream: "multiplier"
@@ -362,7 +362,7 @@ class BeginEndLoopCalculatorGraphWithClonedInputsTest : public ::testing::Test {
             input_stream: "BATCH_END:timestamp"
             output_stream: "ITERABLE:multiplied_ints"
           }
-        )");
+        )pb");
     tool::AddVectorSink("multiplied_ints", &graph_config, &output_packets_);
     MP_ASSERT_OK(graph_.Initialize(graph_config));
     MP_ASSERT_OK(graph_.StartRun({}));

mediapipe/calculators/core/begin_loop_calculator.cc

@@ -42,4 +42,9 @@ REGISTER_CALCULATOR(BeginLoopDetectionCalculator);
 typedef BeginLoopCalculator<std::vector<Matrix>> BeginLoopMatrixCalculator;
 REGISTER_CALCULATOR(BeginLoopMatrixCalculator);
 
+// A calculator to process std::vector<std::vector<Matrix>>.
+typedef BeginLoopCalculator<std::vector<std::vector<Matrix>>>
+    BeginLoopMatrixVectorCalculator;
+REGISTER_CALCULATOR(BeginLoopMatrixVectorCalculator);
+
 }  // namespace mediapipe

mediapipe/calculators/core/begin_loop_calculator.h

@@ -61,7 +61,7 @@ class BeginLoopCalculator : public CalculatorBase {
   using ItemT = typename IterableT::value_type;
 
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     // The below enables processing of timestamp bound updates, and that enables
     // correct timestamp propagation by the companion EndLoopCalculator.
     //
@@ -106,10 +106,10 @@ class BeginLoopCalculator : public CalculatorBase {
       }
     }
 
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) final {
+  absl::Status Process(CalculatorContext* cc) final {
     Timestamp last_timestamp = loop_internal_timestamp_;
     if (!cc->Inputs().Tag("ITERABLE").IsEmpty()) {
       const IterableT& collection =
@@ -139,7 +139,7 @@ class BeginLoopCalculator : public CalculatorBase {
         .AddPacket(MakePacket<Timestamp>(cc->InputTimestamp())
                        .At(Timestamp(loop_internal_timestamp_ - 1)));
 
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
  private:

mediapipe/calculators/core/clip_vector_size_calculator.h

@@ -43,13 +43,13 @@ namespace mediapipe {
 template <typename T>
 class ClipVectorSizeCalculator : public CalculatorBase {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
+  static absl::Status GetContract(CalculatorContract* cc) {
     RET_CHECK(cc->Inputs().NumEntries() == 1);
     RET_CHECK(cc->Outputs().NumEntries() == 1);
 
     if (cc->Options<::mediapipe::ClipVectorSizeCalculatorOptions>()
             .max_vec_size() < 1) {
-      return mediapipe::InternalError(
+      return absl::InternalError(
           "max_vec_size should be greater than or equal to 1.");
     }
 
@@ -60,10 +60,10 @@ class ClipVectorSizeCalculator : public CalculatorBase {
       cc->InputSidePackets().Index(0).Set<int>();
     }
 
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override {
+  absl::Status Open(CalculatorContext* cc) override {
     cc->SetOffset(TimestampDiff(0));
     max_vec_size_ = cc->Options<::mediapipe::ClipVectorSizeCalculatorOptions>()
                         .max_vec_size();
@@ -72,23 +72,23 @@ class ClipVectorSizeCalculator : public CalculatorBase {
         !cc->InputSidePackets().Index(0).IsEmpty()) {
       max_vec_size_ = cc->InputSidePackets().Index(0).Get<int>();
     }
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) override {
+  absl::Status Process(CalculatorContext* cc) override {
     if (max_vec_size_ < 1) {
-      return mediapipe::InternalError(
+      return absl::InternalError(
           "max_vec_size should be greater than or equal to 1.");
     }
     if (cc->Inputs().Index(0).IsEmpty()) {
-      return mediapipe::OkStatus();
+      return absl::OkStatus();
     }
 
     return ClipVectorSize<T>(std::is_copy_constructible<T>(), cc);
   }
 
   template <typename U>
-  mediapipe::Status ClipVectorSize(std::true_type, CalculatorContext* cc) {
+  absl::Status ClipVectorSize(std::true_type, CalculatorContext* cc) {
     auto output = absl::make_unique<std::vector<U>>();
     const std::vector<U>& input_vector =
         cc->Inputs().Index(0).Get<std::vector<U>>();
@@ -100,24 +100,23 @@ class ClipVectorSizeCalculator : public CalculatorBase {
       }
     }
     cc->Outputs().Index(0).Add(output.release(), cc->InputTimestamp());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   template <typename U>
-  mediapipe::Status ClipVectorSize(std::false_type, CalculatorContext* cc) {
+  absl::Status ClipVectorSize(std::false_type, CalculatorContext* cc) {
     return ConsumeAndClipVectorSize<T>(std::is_move_constructible<U>(), cc);
   }
 
   template <typename U>
-  mediapipe::Status ConsumeAndClipVectorSize(std::true_type,
-                                             CalculatorContext* cc) {
+  absl::Status ConsumeAndClipVectorSize(std::true_type, CalculatorContext* cc) {
     auto output = absl::make_unique<std::vector<U>>();
-    mediapipe::StatusOr<std::unique_ptr<std::vector<U>>> input_status =
+    absl::StatusOr<std::unique_ptr<std::vector<U>>> input_status =
         cc->Inputs().Index(0).Value().Consume<std::vector<U>>();
 
     if (input_status.ok()) {
       std::unique_ptr<std::vector<U>> input_vector =
-          std::move(input_status).ValueOrDie();
+          std::move(input_status).value();
       auto begin_it = input_vector->begin();
       auto end_it = input_vector->end();
       if (max_vec_size_ < input_vector->size()) {
@@ -129,13 +128,13 @@ class ClipVectorSizeCalculator : public CalculatorBase {
       return input_status.status();
     }
     cc->Outputs().Index(0).Add(output.release(), cc->InputTimestamp());
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
   template <typename U>
-  mediapipe::Status ConsumeAndClipVectorSize(std::false_type,
-                                             CalculatorContext* cc) {
-    return mediapipe::InternalError(
+  absl::Status ConsumeAndClipVectorSize(std::false_type,
+                                        CalculatorContext* cc) {
+    return absl::InternalError(
         "Cannot copy or move input vectors and clip their size.");
   }
 

mediapipe/calculators/core/clip_vector_size_calculator_test.cc

@@ -38,14 +38,14 @@ void AddInputVector(const std::vector<int>& input, int64 timestamp,
 
 TEST(TestClipIntVectorSizeCalculatorTest, EmptyVectorInput) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "TestClipIntVectorSizeCalculator"
         input_stream: "input_vector"
         output_stream: "output_vector"
         options {
           [mediapipe.ClipVectorSizeCalculatorOptions.ext] { max_vec_size: 1 }
         }
-      )");
+      )pb");
   CalculatorRunner runner(node_config);
 
   std::vector<int> input = {};
@@ -60,14 +60,14 @@ TEST(TestClipIntVectorSizeCalculatorTest, EmptyVectorInput) {
 
 TEST(TestClipIntVectorSizeCalculatorTest, OneTimestamp) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "TestClipIntVectorSizeCalculator"
         input_stream: "input_vector"
         output_stream: "output_vector"
         options {
           [mediapipe.ClipVectorSizeCalculatorOptions.ext] { max_vec_size: 2 }
         }
-      )");
+      )pb");
   CalculatorRunner runner(node_config);
 
   std::vector<int> input = {0, 1, 2, 3};
@@ -85,14 +85,14 @@ TEST(TestClipIntVectorSizeCalculatorTest, OneTimestamp) {
 
 TEST(TestClipIntVectorSizeCalculatorTest, TwoInputsAtTwoTimestamps) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "TestClipIntVectorSizeCalculator"
         input_stream: "input_vector"
         output_stream: "output_vector"
         options {
           [mediapipe.ClipVectorSizeCalculatorOptions.ext] { max_vec_size: 3 }
         }
-      )");
+      )pb");
   CalculatorRunner runner(node_config);
 
   {
@@ -133,7 +133,7 @@ TEST(TestClipUniqueIntPtrVectorSizeCalculatorTest, ConsumeOneTimestamp) {
    * The test needs to send packets that own the data.
    */
   CalculatorGraphConfig graph_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig>(R"pb(
         input_stream: "input_vector"
         node {
           calculator: "TestClipUniqueIntPtrVectorSizeCalculator"
@@ -143,7 +143,7 @@ TEST(TestClipUniqueIntPtrVectorSizeCalculatorTest, ConsumeOneTimestamp) {
             [mediapipe.ClipVectorSizeCalculatorOptions.ext] { max_vec_size: 3 }
           }
         }
-      )");
+      )pb");
 
   std::vector<Packet> outputs;
   tool::AddVectorSink("output_vector", &graph_config, &outputs);
@@ -178,7 +178,7 @@ TEST(TestClipUniqueIntPtrVectorSizeCalculatorTest, ConsumeOneTimestamp) {
 
 TEST(TestClipIntVectorSizeCalculatorTest, SidePacket) {
   CalculatorGraphConfig::Node node_config =
-      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"(
+      ParseTextProtoOrDie<CalculatorGraphConfig::Node>(R"pb(
         calculator: "TestClipIntVectorSizeCalculator"
         input_stream: "input_vector"
         input_side_packet: "max_vec_size"
@@ -186,7 +186,7 @@ TEST(TestClipIntVectorSizeCalculatorTest, SidePacket) {
         options {
           [mediapipe.ClipVectorSizeCalculatorOptions.ext] { max_vec_size: 1 }
         }
-      )");
+      )pb");
   CalculatorRunner runner(node_config);
   // This should override the default of 1 set in the options.
   runner.MutableSidePackets()->Index(0) = Adopt(new int(2));

mediapipe/calculators/core/concatenate_detection_vector_calculator.cc

@@ -1,4 +1,4 @@
-// Copyright 2019 The MediaPipe Authors.
+// Copyright 2019-2020 The MediaPipe Authors.
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -20,14 +20,16 @@
 namespace mediapipe {
 
 // Example config:
+//
 // node {
 //   calculator: "ConcatenateDetectionVectorCalculator"
 //   input_stream: "detection_vector_1"
 //   input_stream: "detection_vector_2"
 //   output_stream: "concatenated_detection_vector"
 // }
+//
 typedef ConcatenateVectorCalculator<::mediapipe::Detection>
     ConcatenateDetectionVectorCalculator;
-REGISTER_CALCULATOR(ConcatenateDetectionVectorCalculator);
+MEDIAPIPE_REGISTER_NODE(ConcatenateDetectionVectorCalculator);
 
 }  // namespace mediapipe

mediapipe/calculators/core/concatenate_normalized_landmark_list_calculator.cc

@@ -16,6 +16,7 @@
 #define MEDIAPIPE_CALCULATORS_CORE_CONCATENATE_NORMALIZED_LIST_CALCULATOR_H_  // NOLINT
 
 #include "mediapipe/calculators/core/concatenate_vector_calculator.pb.h"
+#include "mediapipe/framework/api2/node.h"
 #include "mediapipe/framework/calculator_framework.h"
 #include "mediapipe/framework/formats/landmark.pb.h"
 #include "mediapipe/framework/port/canonical_errors.h"
@@ -23,61 +24,55 @@
 #include "mediapipe/framework/port/status.h"
 
 namespace mediapipe {
+namespace api2 {
 
 // Concatenates several NormalizedLandmarkList protos following stream index
 // order. This class assumes that every input stream contains a
 // NormalizedLandmarkList proto object.
-class ConcatenateNormalizedLandmarkListCalculator : public CalculatorBase {
+class ConcatenateNormalizedLandmarkListCalculator : public Node {
  public:
-  static mediapipe::Status GetContract(CalculatorContract* cc) {
-    RET_CHECK(cc->Inputs().NumEntries() != 0);
-    RET_CHECK(cc->Outputs().NumEntries() == 1);
+  static constexpr Input<NormalizedLandmarkList>::Multiple kIn{""};
+  static constexpr Output<NormalizedLandmarkList> kOut{""};
 
-    for (int i = 0; i < cc->Inputs().NumEntries(); ++i) {
-      cc->Inputs().Index(i).Set<NormalizedLandmarkList>();
-    }
+  MEDIAPIPE_NODE_CONTRACT(kIn, kOut);
 
-    cc->Outputs().Index(0).Set<NormalizedLandmarkList>();
-
-    return mediapipe::OkStatus();
+  static absl::Status UpdateContract(CalculatorContract* cc) {
+    RET_CHECK_GE(kIn(cc).Count(), 1);
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Open(CalculatorContext* cc) override {
-    cc->SetOffset(TimestampDiff(0));
+  absl::Status Open(CalculatorContext* cc) override {
     only_emit_if_all_present_ =
         cc->Options<::mediapipe::ConcatenateVectorCalculatorOptions>()
             .only_emit_if_all_present();
-    return mediapipe::OkStatus();
+    return absl::OkStatus();
   }
 
-  mediapipe::Status Process(CalculatorContext* cc) override {
+  absl::Status Process(CalculatorContext* cc) override {
     if (only_emit_if_all_present_) {
-      for (int i = 0; i < cc->Inputs().NumEntries(); ++i) {
-        if (cc->Inputs().Index(i).IsEmpty()) return mediapipe::OkStatus();
+      for (const auto& input : kIn(cc)) {
+        if (input.IsEmpty()) return absl::OkStatus();
       }
     }
 
     NormalizedLandmarkList output;
-    for (int i = 0; i < cc->Inputs().NumEntries(); ++i) {
-      if (cc->Inputs().Index(i).IsEmpty()) continue;
-      const NormalizedLandmarkList& input =
-          cc->Inputs().Index(i).Get<NormalizedLandmarkList>();
-      for (int j = 0; j < input.landmark_size(); ++j) {
-        const NormalizedLandmark& input_landmark = input.landmark(j);
-        *output.add_landmark() = input_landmark;
+    for (const auto& input : kIn(cc)) {
+      if (input.IsEmpty()) continue;
+      const NormalizedLandmarkList& list = *input;
+      for (int j = 0; j < list.landmark_size(); ++j) {
+        *output.add_landmark() = list.landmark(j);
       }
     }
-    cc->Outputs().Index(0).AddPacket(
-        MakePacket<NormalizedLandmarkList>(output).At(cc->InputTimestamp()));
-    return mediapipe::OkStatus();
+    kOut(cc).Send(std::move(output));
+    return absl::OkStatus();
   }
 
  private:
   bool only_emit_if_all_present_;
 };
+MEDIAPIPE_REGISTER_NODE(ConcatenateNormalizedLandmarkListCalculator);
 
-REGISTER_CALCULATOR(ConcatenateNormalizedLandmarkListCalculator);
-
+}  // namespace api2
 }  // namespace mediapipe
 
 // NOLINTNEXTLINE