Papers › PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop

PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop

30 Mar 2021ICCV 2021 10arXiv:2103.16507archive 2025-07-28

Hongwen Zhang, Yating Tian, Xinchi Zhou, Wanli Ouyang, Yebin Liu, LiMin Wang, Zhenan Sun

Regression-based methods have recently shown promising results in reconstructing human meshes from monocular images. By directly mapping raw pixels to model parameters, these methods can produce parametric models in a feed-forward manner via neural networks. However, minor deviation in parameters may lead to noticeable misalignment between the estimated meshes and image evidences. To address this issue, we propose a Pyramidal Mesh Alignment Feedback (PyMAF) loop to leverage a feature pyramid and rectify the predicted parameters explicitly based on the mesh-image alignment status in our deep regressor. In PyMAF, given the currently predicted parameters, mesh-aligned evidences will be extracted from finer-resolution features accordingly and fed back for parameter rectification. To reduce noise and enhance the reliability of these evidences, an auxiliary pixel-wise supervision is imposed on the feature encoder, which provides mesh-image correspondence guidance for our network to preserve the most related information in spatial features. The efficacy of our approach is validated on several benchmarks, including Human3.6M, 3DPW, LSP, and COCO, where experimental results show that our approach consistently improves the mesh-image alignment of the reconstruction. The project page with code and video results can be found at https://hongwenzhang.github.io/pymaf.

PaperPDFConference PDFCode

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

Code

HongwenZhang/PyMAF officialmentioned on GitHubpytorchNOASSERTION report
Droliven/pymaf_reimplementation mentioned 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 Estimation3D Human Reconstruction3D human pose and shape estimationHuman Mesh Recoveryregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation AGORA PyMAF B-MPJPE 83.3 #5 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA PyMAF B-MVE 78.6 #5 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA PyMAF B-NMJE 92.6 #5 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA PyMAF B-NMVE 87.3 #5 of 11 Archive leaderboard report
3D Human Pose Estimation EMDB PyMAF Average MPJAE (deg) 28.4555 #13 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PyMAF Average MPJAE-PA (deg) 25.7033 #13 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PyMAF Average MPJPE (mm) 131.065 #13 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PyMAF Average MPJPE-PA (mm) 82.8502 #13 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PyMAF Average MVE (mm) 159.956 #13 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PyMAF Average MVE-PA (mm) 98.1305 #13 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PyMAF Jitter (10m/s^3) 81.8447 #13 of 13 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