{"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/direct-multi-view-multi-person-3d-pose","title":"Direct Multi-view Multi-person 3D Pose Estimation","arxiv_id":"2111.04076","date":"2021-11-07","proceeding":"NeurIPS 2021 12","authors":["Tao Wang","Jianfeng Zhang","Yujun Cai","Shuicheng Yan","Jiashi Feng"],"abstract":"We present Multi-view Pose transformer (MvP) for estimating multi-person 3D poses from multi-view images. Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple detected 2D poses as in previous methods, MvP directly regresses the multi-person 3D poses in a clean and efficient way, without relying on intermediate tasks. Specifically, MvP represents skeleton joints as learnable query embeddings and let them progressively attend to and reason over the multi-view information from the input images to directly regress the actual 3D joint locations. To improve the accuracy of such a simple pipeline, MvP presents a hierarchical scheme to concisely represent query embeddings of multi-person skeleton joints and introduces an input-dependent query adaptation approach. Further, MvP designs a novel geometrically guided attention mechanism, called projective attention, to more precisely fuse the cross-view information for each joint. MvP also introduces a RayConv operation to integrate the view-dependent camera geometry into the feature representations for augmenting the projective attention. We show experimentally that our MvP model outperforms the state-of-the-art methods on several benchmarks while being much more efficient. Notably, it achieves 92.3% AP25 on the challenging Panoptic dataset, improving upon the previous best approach [36] by 9.8%. MvP is general and also extendable to recovering human mesh represented by the SMPL model, thus useful for modeling multi-person body shapes. Code and models are available at https://github.com/sail-sg/mvp.","url_abs":"https://arxiv.org/abs/2111.04076v2","url_pdf":"https://arxiv.org/pdf/2111.04076v2.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":"direct-multi-view-multi-person-3d-pose","repo_url":"https://github.com/sail-sg/mvp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"direct-multi-view-multi-person-3d-pose","repo_url":"https://github.com/openxrlab/xrmocap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-multi-person-pose-estimation","task_name":"3D Multi-Person Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-multi-person-pose-estimation-on-campus","task":"3D Multi-Person Pose Estimation","dataset":"Campus","model":"MvP","rank_in_archive_order":10,"of":16,"metrics":{"PCP3D":"96.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-multi-person-pose-estimation-on-cmu","task":"3D Multi-Person Pose Estimation","dataset":"Panoptic","model":"MvP","rank_in_archive_order":3,"of":20,"metrics":{"Average MPJPE (mm)":"15.8"},"uses_additional_data":true},{"leaderboard":"/sota/3d-multi-person-pose-estimation-on-shelf","task":"3D Multi-Person Pose Estimation","dataset":"Shelf","model":"MvP","rank_in_archive_order":12,"of":27,"metrics":{"PCP3D":"97.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.04076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04076"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/sail-sg/mvp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openxrlab/xrmocap","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_violates":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c15434906f804d7f","entry":"match_name_keywords","repo":"sail-sg/mvp","repo_kind":"official","path":"run/train_3d.py","file_url":"https://github.com/sail-sg/mvp/blob/HEAD/run/train_3d.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c15434906f804d7f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}