{"url":"/sota/3d-human-pose-estimation-on-rich","task":{"name":"3D Human Pose Estimation","url":"/task/3d-human-pose-estimation","note":null},"dataset":{"name":"RICH","url":"/dataset/rich"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**3D Human Pose Estimation** is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.","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":["MPJPE","MPVPE","PA-MPJPE","BoSE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MPJPE":null,"MPVPE":null,"PA-MPJPE":null,"BoSE":null}},"counts":{"rows":4,"rows_with_code":1,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"UPose3D (eval only)","metrics":{"MPJPE":"34.7","PA-MPJPE":"32"},"uses_additional_data":true,"paper_date":"2024-04-23","paper":"/paper/upose3d-uncertainty-aware-3d-human-pose","paper_url":"https://arxiv.org/abs/2404.14634v3","paper_title":"UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"SkelFormer (HRNet - eval only)","metrics":{"MPJPE":"44.2","MPVPE":"39.9","PA-MPJPE":"35.6"},"uses_additional_data":true,"paper_date":"2024-04-19","paper":"/paper/skelformer-markerless-3d-pose-and-shape","paper_url":"https://arxiv.org/abs/2404.12625v1","paper_title":"SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"IPMAN-R","metrics":{"BoSE":"71.2%","MPJPE":"79","MPVPE":"89.9","PA-MPJPE":"47.6"},"uses_additional_data":false,"paper_date":"2023-03-31","paper":"/paper/3d-human-pose-estimation-via-intuitive","paper_url":"https://arxiv.org/abs/2303.18246v3","paper_title":"3D Human Pose Estimation via Intuitive Physics","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"WHAM (ViT)","metrics":{"MPJPE":"80","MPVPE":"91.2","PA-MPJPE":"44.3"},"uses_additional_data":false,"paper_date":"2023-12-12","paper":"/paper/wham-reconstructing-world-grounded-humans","paper_url":"https://arxiv.org/abs/2312.07531v2","paper_title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","code":"https://github.com/yohanshin/WHAM","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":9,"n_samples":12,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":3,"n_unverified":9,"n_samples":12,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":3,"n_unverified":9,"n_samples":12,"n_pointer_only_licence":0,"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"}}}