MediaPipe is the simplest way for researchers and developers to build world-class ML solutions and applications for mobile, edge, cloud and the web.

A curated list of awesome TensorFlow Lite models, samples, tutorials, tools and learning resources.

A repository that shares tuning results of trained models generated by Tensorflow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. OpenVINO.

Connecting openFrameworks to Google MediaPipe Machine Learning Framework over UDP

🎥🤟 8 minimalistic templates for tfjs mediapipe handpose and facemesh

这是一个 Flutter Packge 以实现摄像头精确追踪并识别十指的运动路径/轨迹和手势动作, 且输出22个手部关键点以支持更多手势自定义. 基于这个包可以编写业务逻辑将手势信息实时转化为指令信息: 一二三四五, rock, spiderman...还可以对不同手势编写不同特效. 可用于短视频直播特效, 智能硬件等领域, 为人机互动带来更自然丰富的体验

A python wrapper for Mediapipe's Multi-Hand Tracking

Real time webcam face detection, protect yourself from COVID19 with a virtual mask

Cross platform sign language translation with mediapipe

Handtracking mediapipe sample with bitmap RGB input

Virtual backgrounds and more for your webcam

HS Mainz Praxisprojekt - Sign Language Recognition with MediaPipe

Sample implementation of 3D object detection with Intel OpenVINO

Mediapipe sample in gradle.

Android application which uses Mediapipe to detect hands in a live stream from a phone camera📱

A tool to navigate a desktop through the usage of hand gestures. Built using mediapipe.

Project for Multimodal Interaction course (A.Y. 2019/2020), GesturePad