Mediapipe Versions Save

Cross-platform, customizable ML solutions for live and streaming media.

3 years ago

MediaPipe in Python
- Released Python Solution API for MediaPipe Face Mesh and MediaPipe Hands
- Updated Python Solution API for MediaPipe Pose
- Also released usage examples as Google Colabs
MediaPipe Objectron
- Released a faster two-stage pipeline
- Added support for more object classes: shoe, chair, cup and camera
- Released training dataset, (to be) announced in a Google AI Blog post
New Tensor class
- Released as a multi-dimensional tensor data container, supporting multiple backends like CPU, Metal buffer, GL buffer and GL texture 2D
- Added new Tensor-based pre-processing, inference and post-processing calculators in mediapipe/calculators/tensor, branched from existing calculators in mediapipe/calculators/tflite
- Most of the (sub-)graph in mediapipe/modules have been updated to use Tensor and the associated calculators. The plan is to fully migrate all in the repo (and deprecate mediapipe/calculators/tflite by end of 2020.
MediaPipe Hands
- Refactored graphs to depend on the new palm_detection and hand_landmark module.
- Improved model speed for both palm detection and hand landmark.
- Extended the main hand tracking example apps to support multiple hands, to replace the separate multi-hand tracking examples.
MediaPipe Face Detection
- Refactored graphs to depend on the face_detection module.

3 years ago

3 years ago

MediaPipe Instant Motion Tracking that performs AR tracking without initialization or calibration.
- Google Developers Blog post
MediaPipe BlazePose in Python now uses pip install mediapipe instead of building from source. Also published a Colab example.
MediaPipe Iris updated to output a set of 478 3D landmarks, including 468 face landmarks from MediaPipe Face Mesh, with those around the eyes further refined, and 10 additional iris landmarks appended at the end.

3 years ago

MediaPipe Pose for upper-body pose tracking
- Google AI blog post for full and upper body Blazepose
Preview of Python support that runs MediaPipe Pose in Python interpreter

3 years ago

3 years ago

3 years ago

TfLiteTensorsToLandmarksCalculator
- It now always normalizes Z coordinates by image width (as for X) when producing NORM_LANDMARKS output, assuming a weak perspective projection camera model.
- The normalize_z option can be used to further normalize Z coordinates by an additional factor. For instance, normalize_z: 0.4 is now used in hand tracking to better account for the Z coordinate distribution in the training data.
Bug fixes
- Fixes issues on Ubuntu 20.04, resolving #820.
Documentation update
- Added instructions for building for Nvidia Jetson and Raspberry Pi devices with ARM Ubuntu.

4 years ago

MediaPipe Hand * Updated model, documentation and pipeline * Improved hand tracking quality in various scenarios * Added handedness prediction, e.g. left or right hand. * See tweet for visualization
MediaPipe Face Detection * Updated model for front-facing camera * Added model for back-facing camera, which better handles smaller faces
MediaPipe AutoFlip * Updated to use face detection model for back-facing camera
Support for running MediaPipe on Windows - experimental * MediaPipe TFLite CPU desktop live and offline demos only. No TFLite GPU and TensorFlow support yet. * Compiled by MSVC through Bazel. No MinGW and Cygwin support yet. * MediaPipe Android apps are NOT buildable on native Windows yet.
Tracing and profiling MediaPipe graphs - experimental * Support for collecting trace logs on Android, iOS, Linux * To analyze the trace logs, MediaPipe Visualizer
Community related * Awesome MediaPipe: curation of code related to MediaPipe * Slack community for MediaPipe users

4 years ago

4 years ago