</> Code with Papers by Syntology

Papers › Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation

Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation

7 Jul 2021arXiv:2107.03098archive 2025-07-28

Jia Li, Linhua Xiang, Jiwei Chen, Zengfu Wang

We propose a simple yet reliable bottom-up approach with a good trade-off between accuracy and efficiency for the problem of multi-person pose estimation. Given an image, we employ an Hourglass Network to infer all the keypoints from different persons indiscriminately as well as the guiding offsets connecting the adjacent keypoints belonging to the same persons. Then, we greedily group the candidate keypoints into multiple human poses (if any), utilizing the predicted guiding offsets. And we refer to this process as greedy offset-guided keypoint grouping (GOG). Moreover, we revisit the encoding-decoding method for the multi-person keypoint coordinates and reveal some important facts affecting accuracy. Experiments have demonstrated the obvious performance improvements brought by the introduced components. Our approach is comparable to the state of the art on the challenging COCO dataset under fair conditions. The source code and our pre-trained model are publicly available online.

PaperPDFCode

Code

hellojialee/OffsetGuided officialmentioned in papermentioned on GitHubpytorch 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 EstimationKeypoint DetectionMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Person Pose Estimation COCO test-dev Hourglass-104 AP 65.6 #12 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev Hourglass-104 APL 68.8 #12 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev Hourglass-104 APM 63.3 #12 of 15 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Hourglass-104 AP Easy 73.8 #19 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Hourglass-104 AP Hard 54.8 #19 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Hourglass-104 AP Medium 66.2 #19 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Hourglass-104 FPS 14.7 (21.4) #19 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Hourglass-104 mAP @0.5:0.95 65.2 #19 of 28 Archive leaderboard report
Pose Estimation CrowdPose Hourglass-104 AP 65.2 #11 of 12 Archive leaderboard report
Pose Estimation CrowdPose Hourglass-104 AP50 85.9 #11 of 12 Archive leaderboard report
Pose Estimation CrowdPose Hourglass-104 AP75 69.5 #11 of 12 Archive leaderboard report
Pose Estimation CrowdPose Hourglass-104 APM 66.2 #11 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.

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