Papers › Single-Stage Multi-Person Pose Machines

Single-Stage Multi-Person Pose Machines

24 Aug 2019ICCV 2019 10arXiv:1908.09220archive 2025-07-28

Xuecheng Nie, Jianfeng Zhang, Shuicheng Yan, Jiashi Feng

Multi-person pose estimation is a challenging problem. Existing methods are mostly two-stage based--one stage for proposal generation and the other for allocating poses to corresponding persons. However, such two-stage methods generally suffer low efficiency. In this work, we present the first single-stage model, Single-stage multi-person Pose Machine (SPM), to simplify the pipeline and lift the efficiency for multi-person pose estimation. To achieve this, we propose a novel Structured Pose Representation (SPR) that unifies person instance and body joint position representations. Based on SPR, we develop the SPM model that can directly predict structured poses for multiple persons in a single stage, and thus offer a more compact pipeline and attractive efficiency advantage over two-stage methods. In particular, SPR introduces the root joints to indicate different person instances and human body joint positions are encoded into their displacements w.r.t. the roots. To better predict long-range displacements for some joints, SPR is further extended to hierarchical representations. Based on SPR, SPM can efficiently perform multi-person poses estimation by simultaneously predicting root joints (location of instances) and body joint displacements via CNNs. Moreover, to demonstrate the generality of SPM, we also apply it to multi-person 3D pose estimation. Comprehensive experiments on benchmarks MPII, extended PASCAL-Person-Part, MSCOCO and CMU Panoptic clearly demonstrate the state-of-the-art efficiency of SPM for multi-person 2D/3D pose estimation, together with outstanding accuracy.

PaperPDFConference PDFCode

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

Code

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 Pose EstimationKeypoint DetectionMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection MPII Multi-Person SPM mAP@0.5 78.5% #3 of 9 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev SPM AP 66.9 #10 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev SPM AP50 88.5 #10 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev SPM AP75 72.9 #10 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev SPM APL 73.1 #10 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev SPM APM 62.6 #10 of 15 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose SPM AP Easy 70.3 #20 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose SPM AP Hard 55.7 #20 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose SPM AP Medium 64.5 #20 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose SPM mAP @0.5:0.95 63.7 #20 of 28 Archive leaderboard report
Multi-Person Pose Estimation MPII Multi-Person SPM AP 78.5% #3 of 9 Archive leaderboard report
Multi-Person Pose Estimation OCHuman SPM AP50 67.5 #5 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman SPM AP75 53.2 #5 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman SPM Validation AP 47.6 #5 of 8 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