{"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/pare-part-attention-regressor-for-3d-human","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","arxiv_id":"2104.08527","date":"2021-04-17","proceeding":"ICCV 2021 10","authors":["Muhammed Kocabas","Chun-Hao P. Huang","Otmar Hilliges","Michael J. Black"],"abstract":"Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable. To address this, we introduce a soft attention mechanism, called the Part Attention REgressor (PARE), that learns to predict body-part-guided attention masks. We observe that state-of-the-art methods rely on global feature representations, making them sensitive to even small occlusions. In contrast, PARE's part-guided attention mechanism overcomes these issues by exploiting information about the visibility of individual body parts while leveraging information from neighboring body-parts to predict occluded parts. We show qualitatively that PARE learns sensible attention masks, and quantitative evaluation confirms that PARE achieves more accurate and robust reconstruction results than existing approaches on both occlusion-specific and standard benchmarks. The code and data are available for research purposes at {\\small \\url{https://pare.is.tue.mpg.de/}}","url_abs":"https://arxiv.org/abs/2104.08527v2","url_pdf":"https://arxiv.org/pdf/2104.08527v2.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":"pare-part-attention-regressor-for-3d-human","repo_url":"https://github.com/mkocabas/PARE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-multi-person-pose-estimation","task_name":"3D Multi-Person Pose Estimation"},{"task_slug":"3d-human-pose-and-shape-estimation","task_name":"3D human pose and shape estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-agora","task":"3D Human Pose Estimation","dataset":"AGORA","model":"PARE","rank_in_archive_order":9,"of":11,"metrics":{"B-MPJPE":"146.2","B-MVE":"140.9","B-NMJE":"174.0","B-NMVE":"167.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-emdb","task":"3D Human Pose Estimation","dataset":"EMDB","model":"PARE","rank_in_archive_order":9,"of":13,"metrics":{"Average MPJAE (deg)":"24.673","Average MPJAE-PA (deg)":"22.3842","Average MPJPE (mm)":"113.887","Average MPJPE-PA (mm)":"72.203","Average MVE (mm)":"133.247","Average MVE-PA (mm)":"85.3788","Jitter (10m/s^3)":"75.1137"},"uses_additional_data":false},{"leaderboard":"/sota/3d-multi-person-pose-estimation-on-agora","task":"3D Multi-Person Pose Estimation","dataset":"AGORA","model":"PARE","rank_in_archive_order":2,"of":4,"metrics":{"B-MPJPE":"146.2","B-MVE":"140.9","B-NMJE":"174.0","B-NMVE":"167.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.08527","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}