We present BlazePose GHUM Holistic, a lightweight neural network pipeline for 3D human body landmarks and pose estimation, specifically tailored to real-time on-device inference. BlazePose GHUM Holistic enables motion capture from a single RGB image including avatar control, fitness tracking and AR/VR effects. Our main contributions include i) a novel method for 3D ground truth data acquisition, ii) updated 3D body tracking with additional hand landmarks and iii) full body pose estimation from a monocular image.
@article{arxiv.2206.11678,
title = {BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation},
author = {Ivan Grishchenko and Valentin Bazarevsky and Andrei Zanfir and Eduard Gabriel Bazavan and Mihai Zanfir and Richard Yee and Karthik Raveendran and Matsvei Zhdanovich and Matthias Grundmann and Cristian Sminchisescu},
journal= {arXiv preprint arXiv:2206.11678},
year = {2022}
}
Comments
4 pages, 4 figures; CVPR Workshop on Computer Vision for Augmented and Virtual Reality, New Orleans, LA, 2022