BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation
Ivan Grishchenko, Valentin Bazarevsky, Andrei Zanfir, Eduard Gabriel, Bazavan, Mihai Zanfir, Richard Yee, Karthik Raveendran, Matsvei Zhdanovich,, Matthias Grundmann, Cristian Sminchisescu
TL;DR
BlazePose GHUM Holistic is a lightweight real-time neural network pipeline that estimates 3D human body landmarks and poses from a single RGB image, enabling applications like avatar control and fitness tracking.
Contribution
It introduces a novel method for 3D ground truth data acquisition and updates 3D body tracking with hand landmarks for full body pose estimation from monocular images.
Findings
Enables real-time 3D human pose estimation on-device.
Incorporates additional hand landmarks for detailed tracking.
Supports various applications like AR/VR and fitness.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Human Motion and Animation · Advanced Vision and Imaging