mediapipe uses in face mesh3d, body-hand pose,and object detection
FACE DETECTION MODEL and BODY POSE The face detector is the same BlazeFace model used in MediaPipe Face Detection. Please refer to MediaPipe Face Detection for details.
FACE LANDMARK MODEL
MediaPipe offers open source cross-platform, customizable ML solutions for live and streaming media. End-to-End acceleration: Built-in fast ML inference and processing accelerated even on common hardware. Build once, deploy anywhere: Unified solution works across Android, iOS, desktop/cloud, web and IoT.
1: face mesh 3d: 2. 3D face landmarks 3. Body pose
Face Mesh 468 point 3D face landmarks in video even on mobile devices and web application MediaPipe
mediapipe doc:https://google.github.io/mediapipe/
doc face mesh 3d: https://google.github.io/mediapipe/solutions/face_mesh.html
Demo url live tfjs: https://storage.googleapis.com/tfjs-models/demos/face-landmarks-detection/index.html
github tfjs: https://github.com/tensorflow/tfjs-models/tree/master/face-landmarks-detection
tfjs: https://github.com/tensorflow/tfjs-models/tree/master/face-landmarks-detection/demo