Papers › Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation

Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation

7 Jul 2023arXiv:2307.03833archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ipl-uw/ZeDO-Release officialmentioned on GitHubpytorch report

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

3D Human Pose EstimationImage to 3DPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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