We will be presenting at CVPR 2019 on June 17~20 in Long Beach, CA. Come join us!
MediaPipe is a framework for building multimodal (eg. video, audio, any time series data) applied ML pipelines. With MediaPipe, a perception pipeline can be built as a graph of modular components, including, for instance, inference models (e.g., TensorFlow, TFLite) and media processing functions.
Follow these instructions.
See mobile and desktop examples.
A web-based visualizer is hosted on MediaPipe Visualizer. Please also see instructions here.
- MediaPipe: A Framework for Perceiving and Augmenting Reality, extended abstract for Third Workshop on Computer Vision for AR/VR.
- Full-length draft: MediaPipe: A Framework for Building Perception Pipelines
We welcome contributions. Please follow these guidelines.
We use GitHub issues for tracking requests and bugs. Please post questions to the MediaPipe Stack Overflow with a 'mediapipe' tag.