{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/omnipose-a-multi-scale-framework-for-multi","title":"OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation","arxiv_id":"2103.10180","date":"2021-03-18","proceeding":null,"authors":["Bruno Artacho","Andreas Savakis"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2103.10180v1","url_pdf":"https://arxiv.org/pdf/2103.10180v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"omnipose-a-multi-scale-framework-for-multi","repo_url":"https://github.com/bmartacho/OmniPose","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"hrnet","method_name":"HRNet"},{"method_slug":"heatmap","method_name":"Heatmap"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-coco","task":"Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"OmniPose (WASPv2)","rank_in_archive_order":1,"of":10,"metrics":{"AP":"79.5","AP50":"93.6","AP75":"85.9","APL":"84.6","APM":"76","AR":"81.9"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"OmniPose (WASPv2)","rank_in_archive_order":16,"of":47,"metrics":{"AP":"76.4","AP50":"92.6","AP75":"83.7","APL":"82.6","APM":"72.6","AR":"81.2"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-leeds-sports-poses","task":"Pose Estimation","dataset":"Leeds Sports Poses","model":"OmniPose","rank_in_archive_order":1,"of":18,"metrics":{"PCK":"99.5%"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii","task":"Pose Estimation","dataset":"MPII","model":"OmniPose (WASPv2)","rank_in_archive_order":1,"of":1,"metrics":{"PCKh@0.2":"92.3"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-upenn-action","task":"Pose Estimation","dataset":"UPenn Action","model":"OmniPose","rank_in_archive_order":1,"of":5,"metrics":{"Mean PCK@0.2":"99.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}