Papers › PARE: Part Attention Regressor for 3D Human Body Estimation

PARE: Part Attention Regressor for 3D Human Body Estimation

17 Apr 2021ICCV 2021 10arXiv:2104.08527archive 2025-07-28

Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, Michael J. Black

Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable. To address this, we introduce a soft attention mechanism, called the Part Attention REgressor (PARE), that learns to predict body-part-guided attention masks. We observe that state-of-the-art methods rely on global feature representations, making them sensitive to even small occlusions. In contrast, PARE's part-guided attention mechanism overcomes these issues by exploiting information about the visibility of individual body parts while leveraging information from neighboring body-parts to predict occluded parts. We show qualitatively that PARE learns sensible attention masks, and quantitative evaluation confirms that PARE achieves more accurate and robust reconstruction results than existing approaches on both occlusion-specific and standard benchmarks. The code and data are available for research purposes at {\small \url{https://pare.is.tue.mpg.de/}}

PaperPDFConference PDFCode

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

Code

mkocabas/PARE 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 Multi-Person Pose Estimation3D human pose and shape estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation AGORA PARE B-MPJPE 146.2 #9 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA PARE B-MVE 140.9 #9 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA PARE B-NMJE 174.0 #9 of 11 Archive leaderboard report
3D Human Pose Estimation AGORA PARE B-NMVE 167.7 #9 of 11 Archive leaderboard report
3D Human Pose Estimation EMDB PARE Average MPJAE (deg) 24.673 #9 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PARE Average MPJAE-PA (deg) 22.3842 #9 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PARE Average MPJPE (mm) 113.887 #9 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PARE Average MPJPE-PA (mm) 72.203 #9 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PARE Average MVE (mm) 133.247 #9 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PARE Average MVE-PA (mm) 85.3788 #9 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB PARE Jitter (10m/s^3) 75.1137 #9 of 13 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA PARE B-MPJPE 146.2 #2 of 4 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA PARE B-MVE 140.9 #2 of 4 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA PARE B-NMJE 174.0 #2 of 4 Archive leaderboard report
3D Multi-Person Pose Estimation AGORA PARE B-NMVE 167.7 #2 of 4 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