Papers › Probabilistic Modeling for Human Mesh Recovery

Probabilistic Modeling for Human Mesh Recovery

26 Aug 2021ICCV 2021 10arXiv:2108.11944archive 2025-07-28

Nikos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman, Kostas Daniilidis

This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: https://www.seas.upenn.edu/~nkolot/projects/prohmr.

PaperPDFConference PDFCode

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

Code

nkolot/ProHMR officialmentioned on GitHubpytorchNOASSERTION 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 ReconstructionHuman Mesh RecoveryMulti-Hypotheses 3D Human Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW ProHMR + fitting PA-MPJPE 55.1 #84 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW Biggs [3] PA-MPJPE 59.9 #91 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW ProHMR PA-MPJPE 65 #99 of 119 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR Best-Hypothesis MPJPE (n = 25) - #2 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR Best-Hypothesis PMPJPE (n = 25) 60.1 #2 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR H36M PMPJPE (n = 1) 41.2 #2 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR H36M PMPJPE (n = 25) 36.8 #2 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR Most-Likely Hypothesis PMPJPE (n = 1) 67.3 #2 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR (2D Vis, by MHEntropy) Best-Hypothesis MPJPE (n = 25) - #7 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR (2D Vis, by MHEntropy) Best-Hypothesis PMPJPE (n = 25) 82.6 #7 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR (2D Vis, by MHEntropy) H36M PMPJPE (n = 1) - #7 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR (2D Vis, by MHEntropy) H36M PMPJPE (n = 25) 64.3 #7 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M ProHMR (2D Vis, by MHEntropy) Most-Likely Hypothesis PMPJPE (n = 1) - #7 of 10 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.

Methods

Normalizing Flows

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