Papers › OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation

OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation

18 Mar 2021arXiv:2103.10180archive 2025-07-28

Bruno Artacho, Andreas Savakis

We propose OmniPose, a single-pass, end-to-end trainable framework, that achieves state-of-the-art results for multi-person pose estimation. Using a novel waterfall module, the OmniPose architecture leverages multi-scale feature representations that increase the effectiveness of backbone feature extractors, without the need for post-processing. OmniPose incorporates contextual information across scales and joint localization with Gaussian heatmap modulation at the multi-scale feature extractor to estimate human pose with state-of-the-art accuracy. The multi-scale representations, obtained by the improved waterfall module in OmniPose, leverage the efficiency of progressive filtering in the cascade architecture, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Our results on multiple datasets demonstrate that OmniPose, with an improved HRNet backbone and waterfall module, is a robust and efficient architecture for multi-person pose estimation that achieves state-of-the-art results.

PaperPDFCode

Code

bmartacho/OmniPose officialmentioned 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

Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation COCO (Common Objects in Context) OmniPose (WASPv2) AP 79.5 #1 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) OmniPose (WASPv2) AP50 93.6 #1 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) OmniPose (WASPv2) AP75 85.9 #1 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) OmniPose (WASPv2) APL 84.6 #1 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) OmniPose (WASPv2) APM 76 #1 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) OmniPose (WASPv2) AR 81.9 #1 of 10 Archive leaderboard report
Pose Estimation COCO test-dev OmniPose (WASPv2) AP 76.4 #16 of 47 Archive leaderboard report
Pose Estimation COCO test-dev OmniPose (WASPv2) AP50 92.6 #16 of 47 Archive leaderboard report
Pose Estimation COCO test-dev OmniPose (WASPv2) AP75 83.7 #16 of 47 Archive leaderboard report
Pose Estimation COCO test-dev OmniPose (WASPv2) APL 82.6 #16 of 47 Archive leaderboard report
Pose Estimation COCO test-dev OmniPose (WASPv2) APM 72.6 #16 of 47 Archive leaderboard report
Pose Estimation COCO test-dev OmniPose (WASPv2) AR 81.2 #16 of 47 Archive leaderboard report
Pose Estimation Leeds Sports Poses OmniPose PCK 99.5% #1 of 18 Archive leaderboard report
Pose Estimation MPII OmniPose (WASPv2) PCKh@0.2 92.3 #1 of 1 Archive leaderboard report
Pose Estimation UPenn Action OmniPose Mean PCK@0.2 99.4 #1 of 5 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.

Methods

Batch NormalizationConvolutionHRNetHeatmapReLUResidual Connection

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