Papers › HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation

HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation

8 Jun 2021arXiv:2106.04269archive 2025-07-28

Nermin Samet, Emre Akbas

In this paper, we present a new bottom-up one-stage method for whole-body pose estimation, which we call "hierarchical point regression," or HPRNet for short. In standard body pose estimation, the locations of ∼17 major joints on the human body are estimated. Differently, in whole-body pose estimation, the locations of fine-grained keypoints (68 on face, 21 on each hand and 3 on each foot) are estimated as well, which creates a scale variance problem that needs to be addressed. To handle the scale variance among different body parts, we build a hierarchical point representation of body parts and jointly regress them. The relative locations of fine-grained keypoints in each part (e.g. face) are regressed in reference to the center of that part, whose location itself is estimated relative to the person center. In addition, unlike the existing two-stage methods, our method predicts whole-body pose in a constant time independent of the number of people in an image. On the COCO WholeBody dataset, HPRNet significantly outperforms all previous bottom-up methods on the keypoint detection of all whole-body parts (i.e. body, foot, face and hand); it also achieves state-of-the-art results on face (75.4 AP) and hand (50.4 AP) keypoint detection. Code and models are available at \url{https://github.com/nerminsamet/HPRNet}.

PaperPDFCode

Code

nerminsamet/HPRNet 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 EstimationFace DetectionFacial Landmark DetectionFoot keypoint detectionHand Pose EstimationKeypoint DetectionMulti-Person Pose EstimationPose Estimationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation COCO-WholeBody HPRNet WB 34.8 #13 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HPRNet body 59.4 #13 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HPRNet face 75.4 #13 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HPRNet foot 53.0 #13 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HPRNet hand 50.4 #13 of 15 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (Hourglass-104) AP 56.4 #1 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (Hourglass-104) AP50 82.4 #1 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (Hourglass-104) AP75 67.1 #1 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (Hourglass-104) APL 63.3 #1 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (Hourglass-104) APM 43.4 #1 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (DLA) AP 55.8 #2 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (DLA) AP50 82.3 #2 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (DLA) AP75 66.2 #2 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (DLA) APL 63.6 #2 of 2 Archive leaderboard report
Face Detection COCO-WholeBody HPRNet (DLA) APM 40 #2 of 2 Archive leaderboard report
Facial Landmark Detection COCO-WholeBody HPRNet (Hourglass-104) keypoint AP 75.4 #1 of 2 Archive leaderboard report
Facial Landmark Detection COCO-WholeBody HPRNet (DLA) keypoint AP 74.6 #2 of 2 Archive leaderboard report
Hand Pose Estimation COCO-WholeBody HPRNet (Hourglass-104) keypoint AP 50.4 #1 of 2 Archive leaderboard report
Hand Pose Estimation COCO-WholeBody HPRNet (DLA) keypoint AP 47 #2 of 2 Archive leaderboard report
Multi-Person Pose Estimation COCO-WholeBody HPRNet (Hourglass-104) keypoint AP 59.4 #1 of 2 Archive leaderboard report
Multi-Person Pose Estimation COCO-WholeBody HPRNet (DLA) keypoint AP 55.2 #2 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.

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