{"url":"/task/hand-pose-estimation","name":"Hand Pose Estimation","slug":"hand-pose-estimation","description_markdown":"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>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":260,"papers_with_code":103,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":23,"subtasks":1,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/hand-pose-estimation-on-nyu-hands","slug":"hand-pose-estimation-on-nyu-hands","dataset":"NYU Hands","dataset_url":"/dataset/nyu-hand","rows_in_archive":17,"metrics":["Average 3D Error","FPS"],"first_row_in_archive_order":{"model":"Virtual View Selection","paper_title":"Efficient Virtual View Selection for 3D Hand Pose Estimation","paper_url":"/paper/efficient-virtual-view-selection-for-3d-hand","paper_date":"2022-03-29","arxiv_id":"2203.15458","code_links":[{"title":"iscas3dv/handpose-virtualview","url":"https://github.com/iscas3dv/handpose-virtualview"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-icvl-hands","slug":"hand-pose-estimation-on-icvl-hands","dataset":"ICVL Hands","dataset_url":"/dataset/icvl","rows_in_archive":15,"metrics":["Average 3D Error","FPS"],"first_row_in_archive_order":{"model":"Virtual View Selection","paper_title":"Efficient Virtual View Selection for 3D Hand Pose Estimation","paper_url":"/paper/efficient-virtual-view-selection-for-3d-hand","paper_date":"2022-03-29","arxiv_id":"2203.15458","code_links":[{"title":"iscas3dv/handpose-virtualview","url":"https://github.com/iscas3dv/handpose-virtualview"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-msra-hands","slug":"hand-pose-estimation-on-msra-hands","dataset":"MSRA Hands","dataset_url":"/dataset/msra-hand","rows_in_archive":11,"metrics":["Average 3D Error"],"first_row_in_archive_order":{"model":"TriHorn-Net","paper_title":"TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation","paper_url":"/paper/trihorn-net-a-model-for-accurate-depth-based","paper_date":"2022-06-14","arxiv_id":"2206.07117","code_links":[{"title":"mrezaei92/TriHorn-Net","url":"https://github.com/mrezaei92/TriHorn-Net"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-hands-2017","slug":"hand-pose-estimation-on-hands-2017","dataset":"HANDS 2017","dataset_url":null,"rows_in_archive":9,"metrics":["Average 3D Error"],"first_row_in_archive_order":{"model":"AWR","paper_title":"AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation","paper_url":"/paper/awr-adaptive-weighting-regression-for-3d-hand","paper_date":"2020-07-19","arxiv_id":"2007.09590","code_links":[{"title":"Elody-07/AWR-Adaptive-Weighting-Regression","url":"https://github.com/Elody-07/AWR-Adaptive-Weighting-Regression"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/hand-pose-estimation-on-hands-2019","slug":"hand-pose-estimation-on-hands-2019","dataset":"HANDS 2019","dataset_url":null,"rows_in_archive":3,"metrics":["Average 3D Error"],"first_row_in_archive_order":{"model":"Ours-15views","paper_title":"Efficient Virtual View Selection for 3D Hand Pose Estimation","paper_url":"/paper/efficient-virtual-view-selection-for-3d-hand","paper_date":"2022-03-29","arxiv_id":"2203.15458","code_links":[{"title":"iscas3dv/handpose-virtualview","url":"https://github.com/iscas3dv/handpose-virtualview"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-coco-wholebody","slug":"hand-pose-estimation-on-coco-wholebody","dataset":"COCO-WholeBody","dataset_url":"/dataset/coco-wholebody","rows_in_archive":2,"metrics":["keypoint AP"],"first_row_in_archive_order":{"model":"HPRNet (Hourglass-104)","paper_title":"HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation","paper_url":"/paper/hprnet-hierarchical-point-regression-for","paper_date":"2021-06-08","arxiv_id":"2106.04269","code_links":[{"title":"nerminsamet/HPRNet","url":"https://github.com/nerminsamet/HPRNet"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-3dpw","slug":"hand-pose-estimation-on-3dpw","dataset":"3DPW","dataset_url":"/dataset/3dpw","rows_in_archive":1,"metrics":["MPJPE"],"first_row_in_archive_order":{"model":"Hand4Whole","paper_title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","paper_url":"/paper/pose2pose-3d-positional-pose-guided-3d","paper_date":"2020-11-23","arxiv_id":"2011.11534","code_links":[{"title":"mks0601/Hand4Whole_RELEASE","url":"https://github.com/mks0601/Hand4Whole_RELEASE"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-custom-finngers","slug":"hand-pose-estimation-on-custom-finngers","dataset":"Custom FINNgers","dataset_url":"/dataset/custom-finngers","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"FINNger","paper_title":"FINNger -- Applying artificial intelligence to ease math learning for children","paper_url":"/paper/finnger-applying-artificial-intelligence-to","paper_date":"2021-05-26","arxiv_id":"2105.12281","code_links":[{"title":"rafaeelaudibert/FINNger","url":"https://github.com/rafaeelaudibert/FINNger"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-icvl","slug":"hand-pose-estimation-on-icvl","dataset":"ICVL","dataset_url":"/dataset/icvl","rows_in_archive":1,"metrics":["Error (mm)"],"first_row_in_archive_order":{"model":"Ours-15views","paper_title":"Efficient Virtual View Selection for 3D Hand Pose Estimation","paper_url":"/paper/efficient-virtual-view-selection-for-3d-hand","paper_date":"2022-03-29","arxiv_id":"2203.15458","code_links":[{"title":"iscas3dv/handpose-virtualview","url":"https://github.com/iscas3dv/handpose-virtualview"}],"syntology":null}},{"leaderboard":"/sota/hand-pose-estimation-on-k2hpd","slug":"hand-pose-estimation-on-k2hpd","dataset":"K2HPD","dataset_url":"/dataset/k2hpd","rows_in_archive":1,"metrics":["PDJ@5mm"],"first_row_in_archive_order":{"model":"A2J","paper_title":"A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image","paper_url":"/paper/a2j-anchor-to-joint-regression-network-for-3d","paper_date":"2019-08-27","arxiv_id":"1908.09999","code_links":[{"title":"zhangboshen/A2J","url":"https://github.com/zhangboshen/A2J"},{"title":"bo-zhang-cs/CACNet-Pytorch","url":"https://github.com/bo-zhang-cs/CACNet-Pytorch"}],"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/3dpw","name":"3DPW","full_name":"","num_papers_in_archive":395},{"url":"/dataset/rhd","name":"RHD","full_name":"Rendered Hand Pose","num_papers_in_archive":75},{"url":"/dataset/interhand2-6m","name":"InterHand2.6M","full_name":"","num_papers_in_archive":50},{"url":"/dataset/coco-wholebody","name":"COCO-WholeBody","full_name":"","num_papers_in_archive":33},{"url":"/dataset/arctic","name":"ARCTIC","full_name":"Articulated Objects in Free-form Hand Interaction","num_papers_in_archive":23},{"url":"/dataset/icvl","name":"ICVL","full_name":null,"num_papers_in_archive":17},{"url":"/dataset/3d-hand-pose","name":"3D Hand Pose","full_name":"","num_papers_in_archive":16},{"url":"/dataset/nyu-hand","name":"NYU Hand","full_name":"NYU Hand","num_papers_in_archive":16},{"url":"/dataset/first-person-hand-action-benchmark","name":"First-Person Hand Action Benchmark","full_name":"","num_papers_in_archive":15},{"url":"/dataset/msra-hand","name":"MSRA Hand","full_name":"MSRA Hand","num_papers_in_archive":15},{"url":"/dataset/egodexter","name":"EgoDexter","full_name":"EgoDexter","num_papers_in_archive":13},{"url":"/dataset/hic","name":"HIC","full_name":"Hands in Action","num_papers_in_archive":12},{"url":"/dataset/handnet","name":"HandNet","full_name":"","num_papers_in_archive":7},{"url":"/dataset/synthhands","name":"SynthHands","full_name":"SynthHands","num_papers_in_archive":7},{"url":"/dataset/icvl-hand-posture","name":"ICVL Hand Posture","full_name":"ICVL Hand Posture Dataset","num_papers_in_archive":3},{"url":"/dataset/k2hpd","name":"K2HPD","full_name":"","num_papers_in_archive":3},{"url":"/dataset/contactart","name":"ContactArt","full_name":"","num_papers_in_archive":2},{"url":"/dataset/muvihand","name":"MuViHand","full_name":"","num_papers_in_archive":2},{"url":"/dataset/thermohands","name":"ThermoHands","full_name":"","num_papers_in_archive":2},{"url":"/dataset/bighand2-2m-benchmark","name":"BigHand2.2M Benchmark","full_name":"","num_papers_in_archive":1},{"url":"/dataset/custom-finngers","name":"Custom FINNgers","full_name":"","num_papers_in_archive":1},{"url":"/dataset/surgical-hands","name":"Surgical Hands","full_name":"","num_papers_in_archive":1},{"url":"/dataset/human-palm-and-gloves-dataset-human-body","name":"Human Palm and Gloves Dataset | Human Body Parts Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-hand-pose-estimation","name":"3D Hand Pose Estimation"}],"parent_tasks":[{"url":"/task/hand","name":"Hand"},{"url":"/task/pose-estimation","name":"Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":103,"tagged_in_all":260,"items":[{"url":"/paper/learning-from-simulated-and-unsupervised","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","date":"2016-12-22","arxiv_id":"1612.07828","repositories_listed":9,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/learning-to-estimate-3d-hand-pose-from-single","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","date":"2017-05-03","arxiv_id":"1705.01389","repositories_listed":8,"syntology":null},{"url":"/paper/v2v-posenet-voxel-to-voxel-prediction-network","title":"V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map","date":"2017-11-20","arxiv_id":"1711.07399","repositories_listed":5,"syntology":null},{"url":"/paper/weakly-supervised-mesh-convolutional-hand","title":"Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild","date":"2020-04-04","arxiv_id":"2004.01946","repositories_listed":4,"syntology":{"n":20,"n_ran":11,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/ho-3d-a-multi-user-multi-object-dataset-for","title":"HOnnotate: A method for 3D Annotation of Hand and Object Poses","date":"2019-07-02","arxiv_id":"1907.01481","repositories_listed":4,"syntology":null},{"url":"/paper/deepprior-improving-fast-and-accurate-3d-hand","title":"DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation","date":"2017-08-28","arxiv_id":"1708.08325","repositories_listed":4,"syntology":null},{"url":"/paper/weakly-supervised-gaze-estimation-from","title":"3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views","date":"2022-12-06","arxiv_id":"2212.02997","repositories_listed":3,"syntology":null},{"url":"/paper/simba-specific-identity-markers-for-bone-age","title":"SIMBA: Specific Identity Markers for Bone Age Assessment","date":"2020-07-10","arxiv_id":"2007.05454","repositories_listed":3,"syntology":null},{"url":"/paper/single-to-dual-view-adaptation-for-egocentric","title":"Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation","date":"2024-03-07","arxiv_id":"2403.04381","repositories_listed":2,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":16}},{"url":"/paper/mpt-mesh-pre-training-with-transformers-for","title":"MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction","date":"2022-11-24","arxiv_id":"2211.13357","repositories_listed":2,"syntology":null},{"url":"/paper/roft-real-time-optical-flow-aided-6d-object","title":"ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking","date":"2021-11-06","arxiv_id":"2111.03821","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-3d-hand-pose-estimation-from","title":"PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning","date":"2021-06-10","arxiv_id":"2106.05953","repositories_listed":2,"syntology":null},{"url":"/paper/dexycb-a-benchmark-for-capturing-hand","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","date":"2021-04-09","arxiv_id":"2104.04631","repositories_listed":2,"syntology":null},{"url":"/paper/handtailor-towards-high-precision-monocular","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","date":"2021-02-18","arxiv_id":"2102.09244","repositories_listed":2,"syntology":null},{"url":"/paper/interhand2-6m-a-dataset-and-baseline-for-3d","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","date":"2020-08-21","arxiv_id":"2008.09309","repositories_listed":2,"syntology":null},{"url":"/paper/whole-body-human-pose-estimation-in-the-wild","title":"Whole-Body Human Pose Estimation in the Wild","date":"2020-07-23","arxiv_id":"2007.11858","repositories_listed":2,"syntology":null},{"url":"/paper/a2j-anchor-to-joint-regression-network-for-3d","title":"A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image","date":"2019-08-27","arxiv_id":"1908.09999","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/3d-hand-shape-and-pose-estimation-from-a","title":"3D Hand Shape and Pose Estimation from a Single RGB Image","date":"2019-03-03","arxiv_id":"1903.00812","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-hand-mesh-recovery-from-a","title":"End-to-end Hand Mesh Recovery from a Monocular RGB Image","date":"2019-02-25","arxiv_id":"1902.09305","repositories_listed":2,"syntology":null},{"url":"/paper/learning-pose-specific-representations-by","title":"Learning Pose Specific Representations by Predicting Different Views","date":"2018-04-10","arxiv_id":"1804.03390","repositories_listed":2,"syntology":null},{"url":"/paper/monocular-3d-hand-pose-estimation-with","title":"Monocular 3D Hand Pose Estimation with Implicit Camera Alignment","date":"2025-06-10","arxiv_id":"2506.11133","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-synthetic-to-real-domain-gap-in","title":"Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation","date":"2025-03-25","arxiv_id":"2503.19307","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/simhand-mining-similar-hands-for-large-scale","title":"SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training","date":"2025-02-21","arxiv_id":"2502.15251","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/egohand-ego-centric-hand-pose-estimation-and","title":"EgoHand: Ego-centric Hand Pose Estimation and Gesture Recognition with Head-mounted Millimeter-wave Radar and IMUs","date":"2025-01-23","arxiv_id":"2501.13805","repositories_listed":1,"syntology":null},{"url":"/paper/emg2pose-a-large-and-diverse-benchmark-for","title":"emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation","date":"2024-12-02","arxiv_id":"2412.02725","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/wilor-end-to-end-3d-hand-localization-and","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","date":"2024-09-18","arxiv_id":"2409.12259","repositories_listed":1,"syntology":null},{"url":"/paper/sharp-segmentation-of-hands-and-arms-by-range","title":"SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition","date":"2024-08-19","arxiv_id":"2408.10037","repositories_listed":1,"syntology":null},{"url":"/paper/handdagt-a-denoising-adaptive-graph","title":"HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation","date":"2024-07-30","arxiv_id":"2407.20542","repositories_listed":1,"syntology":null},{"url":"/paper/ho-cap-a-capture-system-and-dataset-for-3d","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","date":"2024-06-10","arxiv_id":"2406.06843","repositories_listed":1,"syntology":null},{"url":"/paper/in-my-perspective-in-my-hands-accurate","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","date":"2024-04-14","arxiv_id":"2404.09308","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}