Papers › Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph...
Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks
Yujun Cai, Liuhao Ge, Jun Liu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan, Nadia Magnenat Thalmann
Despite great progress in 3D pose estimation from single-view images or videos, it remains a challenging task due to the substantial depth ambiguity and severe self-occlusions. Motivated by the effectiveness of incorporating spatial dependencies and temporal consistencies to alleviate these issues, we propose a novel graph-based method to tackle the problem of 3D human body and 3D hand pose estimation from a short sequence of 2D joint detections. Particularly, domain knowledge about the human hand (body) configurations is explicitly incorporated into the graph convolutional operations to meet the specific demand of the 3D pose estimation. Furthermore, we introduce a local-to-global network architecture, which is capable of learning multi-scale features for the graph-based representations. We evaluate the proposed method on challenging benchmark datasets for both 3D hand pose estimation and 3D body pose estimation. Experimental results show that our method achieves state-of-the-art performance on both tasks.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=7) | Average MPJPE (mm) | 48.8 | #54 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=7) | Multi-View or Monocular | Monocular | #54 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=7) | Using 2D ground-truth joints | No | #54 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=3) | Average MPJPE (mm) | 49.1 | #55 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=3) | Multi-View or Monocular | Monocular | #55 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=3) | Using 2D ground-truth joints | No | #55 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=1) | Average MPJPE (mm) | 50.6 | #67 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=1) | Multi-View or Monocular | Monocular | #67 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | STRGCN (T=1) | Using 2D ground-truth joints | No | #67 of 88 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections