3D Pose Detection with MediaPipe BlazePose GHUM and TensorFlow.js — The TensorFlow Blog

3D pose estimation opens up new design opportunities for applications such as fitness, medical, motion capture and beyond

これすごい

There are some pros and cons of using each runtime. As shown in the performance table below, the MediaPipe runtime provides faster inference speed on desktop, laptop and android phones. The TF.js runtime provides faster inference speed on iPhones and iPads. The TF.js runtime is also about 1 MB smaller than the MediaPipe runtime.

BlazePose

ボトルネックの推論部分が

mediapipe = wasm

desktop > mobile

tfjs = webgl

mobile > desktop

pixelでは wasm > webgl

cpu intensiveかgpu intensiveか

wasmが速くなっていくことに期待