3D Multi-Person Pose Estimation
This task aims to solve root-relative 3D multi-person pose estimation. No human bounding box and root joint coordinate groundtruth are used in testing time.
( Image credit: RootNet )
Papers
Showing 1–10 of 62 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement | 3DPCK | 89.9 | — | Unverified |
| 2 | Multi-HMR | 3DPCK | 89.5 | — | Unverified |
| 3 | Unsupervised Cross-Modal Alignment | 3DPCK | 78.4 | — | Unverified |
| 4 | MUG | 3DPCK | 76.27 | — | Unverified |
| 5 | 3DCrowdNet | 3DPCK | 76.2 | — | Unverified |
| 6 | SelecSLS | 3DPCK | 75.8 | — | Unverified |
| 7 | HG-RCNN | 3DPCK | 74.2 | — | Unverified |
| 8 | BMP | 3DPCK | 73.83 | — | Unverified |
| 9 | 3DCrowdNet (HigherHRNet) | 3DPCK | 72.7 | — | Unverified |