{"url":"/sota/3d-multi-person-human-pose-estimation-on","task":{"name":"3D Multi-Person Pose Estimation","url":"/task/3d-multi-person-pose-estimation","note":null},"dataset":{"name":"MuPoTS-3D","url":"/dataset/mupots-3d"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"This task aims to solve root-relative 3D multi-person pose estimation. No human bounding box and root joint coordinate groundtruth are used in testing time.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [RootNet](https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["3DPCK"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"3DPCK":null}},"counts":{"rows":10,"rows_with_code":8,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement","metrics":{"3DPCK":"89.9"},"uses_additional_data":true,"paper_date":"2022-10-24","paper":"/paper/multi-person-3d-pose-and-shape-estimation-via","paper_url":"https://arxiv.org/abs/2210.13529v2","paper_title":"Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement","code":"https://github.com/JunukCha/MultiPerson","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Multi-HMR","metrics":{"3DPCK":"89.5"},"uses_additional_data":true,"paper_date":"2024-02-22","paper":"/paper/multi-hmr-multi-person-whole-body-human-mesh","paper_url":"https://arxiv.org/abs/2402.14654v2","paper_title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","code":"https://github.com/naver/multi-hmr","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":3,"model":"Temporal Smoothing","metrics":{"3DPCK":"85.3"},"uses_additional_data":false,"paper_date":"2020-10-31","paper":"/paper/temporal-smoothing-for-3d-human-pose","paper_url":"https://arxiv.org/abs/2011.00250v1","paper_title":"Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People","code":"https://github.com/vegesm/pose_refinement","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Unsupervised Cross-Modal Alignment","metrics":{"3DPCK":"78.4"},"uses_additional_data":false,"paper_date":"2020-08-04","paper":"/paper/unsupervised-cross-modal-alignment-for-multi","paper_url":"https://arxiv.org/abs/2008.01388v1","paper_title":"Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation","code":"https://github.com/revanurambareesh/multiperson","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"MUG","metrics":{"3DPCK":"76.27"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/mug-multi-human-graph-network-for-3d-mesh","paper_url":"https://arxiv.org/abs/2205.12583v3","paper_title":"MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"3DCrowdNet","metrics":{"3DPCK":"76.2"},"uses_additional_data":false,"paper_date":"2023-04-10","paper":"/paper/three-recipes-for-better-3d-pseudo-gts-of-3d","paper_url":"https://arxiv.org/abs/2304.04875v1","paper_title":"Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild","code":"https://github.com/mks0601/NeuralAnnot_RELEASE","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"SelecSLS","metrics":{"3DPCK":"75.8"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/xnect-real-time-multi-person-3d-human-pose","paper_url":"https://arxiv.org/abs/1907.00837v2","paper_title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":4,"syntology":null},{"rank_in_archive_order":8,"model":"HG-RCNN","metrics":{"3DPCK":"74.2"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/multi-person-3d-human-pose-estimation-from","paper_url":"https://arxiv.org/abs/1909.10854v1","paper_title":"Multi-Person 3D Human Pose Estimation from Monocular Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"BMP","metrics":{"3DPCK":"73.83"},"uses_additional_data":false,"paper_date":"2021-05-06","paper":"/paper/body-meshes-as-points","paper_url":"https://arxiv.org/abs/2105.02467v2","paper_title":"Body Meshes as Points","code":"https://github.com/jfzhang95/BMP","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"3DCrowdNet (HigherHRNet)","metrics":{"3DPCK":"72.7"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/3dcrowdnet-2d-human-pose-guided3d-crowd-human","paper_url":"https://arxiv.org/abs/2104.07300v3","paper_title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","code":"https://github.com/hongsukchoi/3dcrowdnet_release","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":14,"n_unverified":13,"n_samples":27,"n_pointer_only_licence":11,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":13,"n_samples":27,"n_pointer_only_licence":11,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}