Papers › RMPE: Regional Multi-person Pose Estimation

RMPE: Regional Multi-person Pose Estimation

1 Dec 2016ICCV 2017 10arXiv:1612.00137archive 2025-07-28

Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu

Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. Our framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG). Our method is able to handle inaccurate bounding boxes and redundant detections, allowing it to achieve a 17% increase in mAP over the state-of-the-art methods on the MPII (multi person) dataset.Our model and source codes are publicly available.

PaperPDFConference PDFCode

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

Code

14 repositories listed; official and paper-mentioned ones first.

2023-MindSpore-1/ms-code-199 mentioned on GitHubmindspore report
Fangyh09/pose_nms mentioned on GitHub report
MVIG-SJTU/RMPE mentioned on GitHubtorchNOASSERTION report
ManifoldFR/recvis-project mentioned on GitHubtf report
MattyChoi/PoseMachines mentioned on GitHubpytorch report
lyqcom/alphapose mentioned on GitHubmindsporeApache-2.0 report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
MVIG-SJTU/AlphaPose pytorchNOASSERTION 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

2D Human Pose EstimationHuman DetectionKeypoint DetectionMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation OCHuman RMPE Test AP 30.7 #8 of 11 Archive leaderboard report
2D Human Pose Estimation OCHuman RMPE Validation AP 38.8 #8 of 11 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) AlphaPose FPS 23 #11 of 24 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) AlphaPose Test AP 73.3 #11 of 24 Archive leaderboard report
Keypoint Detection COCO test-dev AlphaPose APL 81.5 #16 of 16 Archive leaderboard report
Keypoint Detection MPII Multi-Person AlphaPose mAP@0.5 82.1% #1 of 9 Archive leaderboard report
Keypoint Detection OCHuman RMPE Test AP 30.7 #7 of 10 Archive leaderboard report
Keypoint Detection OCHuman RMPE Validation AP 38.8 #7 of 10 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev RMPE AP 61.8 #15 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev RMPE AP50 83.7 #15 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev RMPE AP75 69.8 #15 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev RMPE APL 67.6 #15 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev RMPE APM 58.6 #15 of 15 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose AlphaPose AP Easy 71.2 #21 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose AlphaPose AP Hard 51.1 #21 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose AlphaPose AP Medium 61.4 #21 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose AlphaPose mAP @0.5:0.95 61.0 #21 of 28 Archive leaderboard report
Multi-Person Pose Estimation MPII Multi-Person AlphaPose AP 82.1% #1 of 9 Archive leaderboard report
Pose Estimation COCO test-dev RMPE++ AP 72.3 #27 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE++ AP50 89.2 #27 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE++ AP75 79.1 #27 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE++ APL 78.6 #27 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE++ APM 68.0 #27 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE AP 61.8 #45 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE AP50 83.7 #45 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE AP75 69.8 #45 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE APL 67.6 #45 of 47 Archive leaderboard report
Pose Estimation COCO test-dev RMPE APM 58.6 #45 of 47 Archive leaderboard report
Pose Estimation OCHuman RMPE Test AP 30.7 #16 of 19 Archive leaderboard report
Pose Estimation OCHuman RMPE Validation AP 38.8 #16 of 19 Archive leaderboard report
Pose Estimation UAV-Human AlphaPose mAP 56.9 #1 of 2 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

Spatial Transformer

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