Papers › SMPR: Single-Stage Multi-Person Pose Regression
SMPR: Single-Stage Multi-Person Pose Regression
Junqi Lin, Huixin Miao, Junjie Cao, Zhixun Su, Risheng Liu
Existing multi-person pose estimators can be roughly divided into two-stage approaches (top-down and bottom-up approaches) and one-stage approaches. The two-stage methods either suffer high computational redundancy for additional person detectors or group keypoints heuristically after predicting all the instance-free keypoints. The recently proposed single-stage methods do not rely on the above two extra stages but have lower performance than the latest bottom-up approaches. In this work, a novel single-stage multi-person pose regression, termed SMPR, is presented. It follows the paradigm of dense prediction and predicts instance-aware keypoints from every location. Besides feature aggregation, we propose better strategies to define positive pose hypotheses for training which all play an important role in dense pose estimation. The network also learns the scores of estimated poses. The pose scoring strategy further improves the pose estimation performance by prioritizing superior poses during non-maximum suppression (NMS). We show that our method not only outperforms existing single-stage methods and but also be competitive with the latest bottom-up methods, with 70.2 AP and 77.5 AP75 on the COCO test-dev pose benchmark. Code is available at https://github.com/cmdi-dlut/SMPR.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Multi-Person Pose Estimation | COCO test-dev | SMPR (HR-Net-32) | AP | 70.2 | #7 of 15 | Archive leaderboard | report |
| Multi-Person Pose Estimation | COCO test-dev | SMPR (HR-Net-32) | AP50 | 89.7 | #7 of 15 | Archive leaderboard | report |
| Multi-Person Pose Estimation | COCO test-dev | SMPR (HR-Net-32) | AP75 | 77.5 | #7 of 15 | Archive leaderboard | report |
| Multi-Person Pose Estimation | COCO test-dev | SMPR (HR-Net-32) | APL | 77.2 | #7 of 15 | Archive leaderboard | report |
| Multi-Person Pose Estimation | COCO test-dev | SMPR (HR-Net-32) | APM | 65.9 | #7 of 15 | 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