Global 3D Human Pose Estimation
1 papers with code • 1 benchmarks • 1 datasets
Global 3D Human Pose Estimation is extending RGB-based human pose estimation to capture errors in global instead of camera-relative coordinate frames. For monocular settings, this task was first introduced by GLAMR (Yuan et al., CVPR 2022).
Most implemented papers
GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
Since the joint reconstruction of human motions and camera poses is underconstrained, we propose a global trajectory predictor that generates global human trajectories based on local body movements.