BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation
This work addresses the problem of efficient 3D motion capture for developers and users in domains such as fitness and augmented reality, though it appears incremental with updates to existing methods.
The paper tackled real-time 3D human pose estimation from a single RGB image, resulting in a lightweight pipeline that enables applications like avatar control and AR/VR effects with on-device inference.
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.