Papers › PoseFix: Model-agnostic General Human Pose Refinement Network

PoseFix: Model-agnostic General Human Pose Refinement Network

10 Dec 2018CVPR 2019 6arXiv:1812.03595archive 2025-07-28

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Multi-person pose estimation from a 2D image is an essential technique for human behavior understanding. In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose. The pose refinement was performed mainly through an end-to-end trainable multi-stage architecture in previous methods. However, they are highly dependent on pose estimation models and require careful model design. By contrast, we propose a model-agnostic pose refinement method. According to a recent study, state-of-the-art 2D human pose estimation methods have similar error distributions. We use this error statistics as prior information to generate synthetic poses and use the synthesized poses to train our model. In the testing stage, pose estimation results of any other methods can be input to the proposed method. Moreover, the proposed model does not require code or knowledge about other methods, which allows it to be easily used in the post-processing step. We show that the proposed approach achieves better performance than the conventional multi-stage refinement models and consistently improves the performance of various state-of-the-art pose estimation methods on the commonly used benchmark. The code is available in this https URL\footnote{\url{https://github.com/mks0601/PoseFix_RELEASE}}.

PaperPDFConference PDFCode

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

Code

mks0601/PoseFix_RELEASE officialmentioned in papermentioned on GitHubtfMIT 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 Estimationmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection COCO (Common Objects in Context) PoseFix(384x288) Test AP 76.7 #4 of 24 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) PoseFix(384x288) Validation AP 77.3 #4 of 24 Archive leaderboard report
Multi-Person Pose Estimation COCO (Common Objects in Context) PoseFix Test AP 76.7 #14 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO (Common Objects in Context) PoseFix Validation AP 77.3 #14 of 15 Archive leaderboard report
Pose Estimation COCO test-dev PoseFix AP 74.7 #22 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseFix AP50 91.2 #22 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseFix AP75 81.9 #22 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseFix APL 81.2 #22 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseFix APM 71.1 #22 of 47 Archive leaderboard report
Pose Estimation COCO test-dev PoseFix AR 79.9 #22 of 47 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