3D Human Pose Estimation On Rich
Metrics
MPJPE
MPVPE
PA-MPJPE
Results
Performance results of various models on this benchmark
Model Name | MPJPE | MPVPE | PA-MPJPE | Paper Title | Repository |
|---|---|---|---|---|---|
| SkelFormer (HRNet - eval only) | 44.2 | 39.9 | 35.6 | SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers | - |
| IPMAN-R | 79 | 89.9 | 47.6 | 3D Human Pose Estimation via Intuitive Physics | - |
| WHAM (ViT) | 80 | 91.2 | 44.3 | WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion | |
| UPose3D (eval only) | 34.7 | - | 32 | UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues | - |
0 of 4 row(s) selected.