3D Human Pose Estimation On Surreal 1
Metrics
MPJPE
PA-MPJPE
PVE
Results
Performance results of various models on this benchmark
Model Name | MPJPE | PA-MPJPE | PVE | Paper Title | Repository |
|---|---|---|---|---|---|
| VirtualMarker | 36.9 | 28.9 | 44.7 | 3D Human Mesh Estimation from Virtual Markers | |
| Cross Dataset Generalization | 37.1 | - | - | Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation | - |
| DynaBOA | - | 34 | 70.7 | Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation | |
| self-supervised mocap | 64.4 | - | - | Self-supervised Learning of Motion Capture | |
| PC-HMR | 51.7 | 37.9 | - | PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos | - |
| BodyNet | 49.1 | - | - | BodyNet: Volumetric Inference of 3D Human Body Shapes |
0 of 6 row(s) selected.