Papers › MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery

MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery

1 Jan 2023ICCV 2023 1archive 2025-07-28

Rongyu Chen, Linlin Yang, Angela Yao

For monocular RGB-based 3D pose and shape estimation, multiple solutions are often feasible due to factors like occlusion and truncation. This work presents a multi-hypothesis probabilistic framework by optimizing the Kullback-Leibler divergence (KLD) between the data and model distribution. Our formulation reveals a connection between the pose entropy and diversity in the multiple hypotheses that has been neglected by previous works. For a comprehensive evaluation, besides the best hypothesis (BH) metric, we factor in visibility for evaluating diversity. Additionally, our framework is label-friendly, in that it can be learned from only partial 2D keypoints, e.g., those that are visible. Experiments on both ambiguous and real-world benchmarks demonstrate that our method outperforms other state-of-the-art multi-hypothesis methods in a comprehensive evaluation. The project page is at https://gloryyrolg.github.io/MHEntropy.

PaperPDFCode

Code

GloryyrolG/MHEntropy officialpytorch 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 Hand Pose Estimation3D Human Pose Estimation3D Human ReconstructionDiversityHuman Mesh RecoveryMulti-Hypotheses 3D Human Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (3D) Best-Hypothesis MPJPE (n = 25) - #1 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (3D) Best-Hypothesis PMPJPE (n = 25) 50.6 #1 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (3D) H36M PMPJPE (n = 1) - #1 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (3D) H36M PMPJPE (n = 25) 36.8 #1 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (3D) Most-Likely Hypothesis PMPJPE (n = 1) - #1 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (2D Vis) Best-Hypothesis MPJPE (n = 25) - #4 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (2D Vis) Best-Hypothesis PMPJPE (n = 25) 66.4 #4 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (2D Vis) H36M PMPJPE (n = 1) - #4 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (2D Vis) H36M PMPJPE (n = 25) 51.3 #4 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M MHEntropy (2D Vis) Most-Likely Hypothesis PMPJPE (n = 1) - #4 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation Human3.6M MHEntropy Average PMPJPE (mm) 36.8 #12 of 12 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