Papers › End-to-end Recovery of Human Shape and Pose

End-to-end Recovery of Human Shape and Pose

18 Dec 2017CVPR 2018 6arXiv:1712.06584archive 2025-07-28

Angjoo Kanazawa, Michael J. Black, David W. Jacobs, Jitendra Malik

We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, we produce a richer and more useful mesh representation that is parameterized by shape and 3D joint angles. The main objective is to minimize the reprojection loss of keypoints, which allow our model to be trained using images in-the-wild that only have ground truth 2D annotations. However, the reprojection loss alone leaves the model highly under constrained. In this work we address this problem by introducing an adversary trained to tell whether a human body parameter is real or not using a large database of 3D human meshes. We show that HMR can be trained with and without using any paired 2D-to-3D supervision. We do not rely on intermediate 2D keypoint detections and infer 3D pose and shape parameters directly from image pixels. Our model runs in real-time given a bounding box containing the person. We demonstrate our approach on various images in-the-wild and out-perform previous optimization based methods that output 3D meshes and show competitive results on tasks such as 3D joint location estimation and part segmentation.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

2023-MindSpore-1/ms-code-27 mentioned on GitHubmindsporeSyntology: not harvested report
Liuxiang0358/HMR mentioned on GitHubmindsporeSyntology: not harvested report
MandyMo/pytorch_HMR mentioned on GitHubpytorchSyntology: not harvested report
ManifoldFR/recvis-project mentioned on GitHubtfSyntology: not harvested report
anilarmagan/HANDS19-Challenge-Toolbox mentioned on GitHubpytorchSyntology: not harvested report
russoale/hmr2.0 mentioned on GitHubtfSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code4 mindsporeSyntology: not harvested report
akanazawa/hmr tfSyntology: not harvested report
open-mmlab/mmpose pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (arXiv:2312.07526; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Hand Pose Estimation3D Human Pose Estimation3D Human Shape Estimation3D Multi-Person Pose EstimationHuman Mesh RecoveryMonocular 3D Human Pose EstimationMulti-Hypotheses 3D Human Pose EstimationWeakly-supervised 3D Human Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW HMR Acceleration Error 37.4 #119 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW HMR MPJPE 130.0 #119 of 119 Archive leaderboard report
3D Human Pose Estimation AGORA HMR B-MPJPE 180.5 #11 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA HMR B-MVE 173.6 #11 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA HMR B-NMJE 226.0 #11 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA HMR B-NMVE 217.0 #11 of 11 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP HMR AUC 36.5 #81 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP HMR MPJPE 124.2 #81 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP HMR PA-MPJPE 89.8 #81 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP HMR PCK 72.9 #81 of 108 Archive leaderboard report
3D Human Shape Estimation SSP-3D HMR(unpaired) PVE-T-SC 20.8 #7 of 11 Archive leaderboard report
3D Human Shape Estimation SSP-3D HMR(unpaired) mIOU 61.0 #7 of 11 Archive leaderboard report
3D Human Shape Estimation SSP-3D HMR PVE-T-SC 22.9 #9 of 11 Archive leaderboard report
3D Human Shape Estimation SSP-3D HMR mIOU 69.0 #9 of 11 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA HMR B-MPJPE 180.5 #4 of 4 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA HMR B-MVE 173.6 #4 of 4 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA HMR B-NMJE 226.0 #4 of 4 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA HMR B-NMVE 217.0 #4 of 4 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HMR Frames Needed 1 #41 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HMR Need Ground Truth 2D Pose No #41 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M HMR Use Video Sequence No #41 of 52 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR (2D Vis, by MHEntropy) Best-Hypothesis MPJPE (n = 25) - #8 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR (2D Vis, by MHEntropy) Best-Hypothesis PMPJPE (n = 25) 85.2 #8 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR (2D Vis, by MHEntropy) H36M PMPJPE (n = 1) 67.4 #8 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR (2D Vis, by MHEntropy) H36M PMPJPE (n = 25) 67.4 #8 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR (2D Vis, by MHEntropy) Most-Likely Hypothesis PMPJPE (n = 1) 85.2 #8 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR Best-Hypothesis MPJPE (n = 25) - #9 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR Best-Hypothesis PMPJPE (n = 25) - #9 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR H36M PMPJPE (n = 1) 56.8 #9 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR H36M PMPJPE (n = 25) 56.8 #9 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HMR Most-Likely Hypothesis PMPJPE (n = 1) - #9 of 10 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M Kanzawa et al. 3D Annotations No #33 of 33 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