3D Multi Person Human Pose Estimation On
Metriken
3DPCK
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement | 89.9 | Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement |
| Multi-HMR | 89.5 | Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot |
| Temporal Smoothing | 85.3 | Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People |
| Unsupervised Cross-Modal Alignment | 78.4 | Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation |
| MUG | 76.27 | MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose |
| 3DCrowdNet | 76.2 | Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild |
| SelecSLS | 75.8 | XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera |
| HG-RCNN | 74.2 | Multi-Person 3D Human Pose Estimation from Monocular Images |
| BMP | 73.83 | Body Meshes as Points |
| 3DCrowdNet (HigherHRNet) | 72.7 | Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes |
0 of 10 row(s) selected.