{"url":"/sota/hand-pose-estimation-on-icvl-hands","task":{"name":"Hand Pose Estimation","url":"/task/hand-pose-estimation","note":null},"dataset":{"name":"ICVL Hands","url":"/dataset/icvl"},"category":"Computer Vision","categories":["Computer Vision","Graphs"],"category_note":null,"description":"Hand pose estimation is the task of finding the joints of the hand from an image or set of video frames.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Pose-REN](https://github.com/xinghaochen/Pose-REN) )</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":["Average 3D Error","FPS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average 3D Error":"lower","FPS":null}},"counts":{"rows":15,"rows_with_code":11,"rows_with_paper_page":15,"rows_dated":15,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Virtual View Selection","metrics":{"Average 3D Error":"4.79"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/efficient-virtual-view-selection-for-3d-hand","paper_url":"https://arxiv.org/abs/2203.15458v1","paper_title":"Efficient Virtual View Selection for 3D Hand Pose Estimation","code":"https://github.com/iscas3dv/handpose-virtualview","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"TriHorn-Net","metrics":{"Average 3D Error":"5.73"},"uses_additional_data":false,"paper_date":"2022-06-14","paper":"/paper/trihorn-net-a-model-for-accurate-depth-based","paper_url":"https://arxiv.org/abs/2206.07117v2","paper_title":"TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation","code":"https://github.com/mrezaei92/TriHorn-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"HandFoldingNet","metrics":{"Average 3D Error":"5.95"},"uses_additional_data":false,"paper_date":"2021-08-12","paper":"/paper/handfoldingnet-a-3d-hand-pose-estimation","paper_url":"https://arxiv.org/abs/2108.05545v1","paper_title":"HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton","code":"https://github.com/cwc1260/handfold","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"AWR","metrics":{"Average 3D Error":"5.98"},"uses_additional_data":false,"paper_date":"2020-07-19","paper":"/paper/awr-adaptive-weighting-regression-for-3d-hand","paper_url":"https://arxiv.org/abs/2007.09590v1","paper_title":"AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation","code":"https://github.com/Elody-07/AWR-Adaptive-Weighting-Regression","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"DePOTR","metrics":{"Average 3D Error":"5.98"},"uses_additional_data":false,"paper_date":"2023-06-12","paper":"/paper/mutr-multi-stage-transformer-for-hand-pose","paper_url":"https://www.mdpi.com/1424-8220/23/12/5509","paper_title":"MuTr: Multi-Stage Transformer for Hand Pose Estimation from Full-Scene Depth Image","code":"https://github.com/mhruz/POTR","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Teacher-Student","metrics":{"Average 3D Error":"5.99"},"uses_additional_data":false,"paper_date":"2023-03-27","paper":"/paper/pushing-the-envelope-for-depth-based-semi","paper_url":"https://arxiv.org/abs/2303.15147v1","paper_title":"Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"PixelwiseRegression","metrics":{"Average 3D Error":"6.152"},"uses_additional_data":false,"paper_date":"2019-05-06","paper":"/paper/pixel-wise-regression-3d-hand-pose-estimation","paper_url":"https://arxiv.org/abs/1905.02085v2","paper_title":"Pixel-wise Regression: 3D Hand Pose Estimation via Spatial-form Representation and Differentiable Decoder","code":"https://github.com/IcarusWizard/PixelwiseRegression","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"V2V-PoseNet","metrics":{"Average 3D Error":"6.28"},"uses_additional_data":false,"paper_date":"2017-11-20","paper":"/paper/v2v-posenet-voxel-to-voxel-prediction-network","paper_url":"http://arxiv.org/abs/1711.07399v3","paper_title":"V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map","code":"https://github.com/mks0601/V2V-PoseNet_RELEASE","n_code_links":5,"syntology":null},{"rank_in_archive_order":9,"model":"A2J","metrics":{"Average 3D Error":"6.461","FPS":"105.06"},"uses_additional_data":false,"paper_date":"2019-08-27","paper":"/paper/a2j-anchor-to-joint-regression-network-for-3d","paper_url":"https://arxiv.org/abs/1908.09999v1","paper_title":"A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image","code":"https://github.com/zhangboshen/A2J","n_code_links":2,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"Pose-REN","metrics":{"Average 3D Error":"6.8"},"uses_additional_data":false,"paper_date":"2017-08-11","paper":"/paper/pose-guided-structured-region-ensemble","paper_url":"http://arxiv.org/abs/1708.03416v2","paper_title":"Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation","code":"https://github.com/xinghaochen/Pose-REN","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"SHPR-Net","metrics":{"Average 3D Error":"7.22"},"uses_additional_data":false,"paper_date":"2018-08-06","paper":"/paper/shpr-net-deep-semantic-hand-pose-regression","paper_url":"https://ieeexplore.ieee.org/document/8425735/","paper_title":"SHPR-Net: Deep Semantic Hand Pose Regression From Point Clouds","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Dense Pixel-wise Estimation","metrics":{"Average 3D Error":"7.3"},"uses_additional_data":false,"paper_date":"2017-11-24","paper":"/paper/dense-3d-regression-for-hand-pose-estimation","paper_url":"http://arxiv.org/abs/1711.08996v1","paper_title":"Dense 3D Regression for Hand Pose Estimation","code":"https://github.com/melonwan/denseReg","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Tree Region Ensemble Network","metrics":{"Average 3D Error":"7.31"},"uses_additional_data":false,"paper_date":"2017-07-23","paper":"/paper/towards-good-practices-for-deep-3d-hand-pose","paper_url":"http://arxiv.org/abs/1707.07248v1","paper_title":"Towards Good Practices for Deep 3D Hand Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"REN","metrics":{"Average 3D Error":" 7.5"},"uses_additional_data":false,"paper_date":"2017-02-08","paper":"/paper/region-ensemble-network-improving","paper_url":"http://arxiv.org/abs/1702.02447v2","paper_title":"Region Ensemble Network: Improving Convolutional Network for Hand Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"DeepPrior++","metrics":{"Average 3D Error":" 8.1"},"uses_additional_data":false,"paper_date":"2017-08-28","paper":"/paper/deepprior-improving-fast-and-accurate-3d-hand","paper_url":"http://arxiv.org/abs/1708.08325v1","paper_title":"DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation","code":"https://github.com/mks0601/V2V-PoseNet_RELEASE","n_code_links":4,"syntology":null}],"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 7,081 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":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":15,"n_unverified":2,"n_samples":17,"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":15,"n_unverified":2,"n_samples":17,"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"}}}