Papers › Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation
Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation
Zhongyu Jiang, Zhuoran Zhou, Lei LI, Wenhao Chai, Cheng-Yen Yang, Jenq-Neng Hwang
Learning-based methods have dominated the 3D human pose estimation (HPE) tasks with significantly better performance in most benchmarks than traditional optimization-based methods. Nonetheless, 3D HPE in the wild is still the biggest challenge for learning-based models, whether with 2D-3D lifting, image-to-3D, or diffusion-based methods, since the trained networks implicitly learn camera intrinsic parameters and domain-based 3D human pose distributions and estimate poses by statistical average. On the other hand, the optimization-based methods estimate results case-by-case, which can predict more diverse and sophisticated human poses in the wild. By combining the advantages of optimization-based and learning-based methods, we propose the \textbf{Ze}ro-shot \textbf{D}iffusion-based \textbf{O}ptimization (\textbf{ZeDO}) pipeline for 3D HPE to solve the problem of cross-domain and in-the-wild 3D HPE. Our multi-hypothesis \textit{\textbf{ZeDO}} achieves state-of-the-art (SOTA) performance on Human3.6M, with minMPJPE $51.4$mm, without training with any 2D-3D or image-3D pairs. Moreover, our single-hypothesis \textit{\textbf{ZeDO}} achieves SOTA performance on 3DPW dataset with PA-MPJPE $40.3$mm on cross-dataset evaluation, which even outperforms learning-based methods trained on 3DPW.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 | 3DPW | ZeDO (S=1,J=17) | MPJPE | 69.7 | #65 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | ZeDO (S=1,J=17) | PA-MPJPE | 40.3 | #65 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | ZeDO (Cross Dataset) | MPJPE | 80.9 | #67 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | ZeDO (Cross Dataset) | PA-MPJPE | 42.6 | #67 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | ZeDO (S=50) | AUC | 65.6 | #23 of 108 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | ZeDO (S=50) | MPJPE | 55.2 | #23 of 108 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | ZeDO (S=50) | PCK | 93 | #23 of 108 | 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