{"url":"/dataset/ho-3d","name":"HO-3D v2","full_name":null,"description_markdown":"A hand-object interaction dataset with 3D pose annotations of hand and object. The dataset contains 66,034 training images and 11,524 test images from a total of 68 sequences. The sequences are captured in multi-camera and single-camera setups and contain 10 different subjects manipulating 10 different objects from YCB dataset. The annotations are automatically obtained using an optimization algorithm. The hand pose annotations for the test set are withheld and the accuracy of the algorithms on the test set can be evaluated with standard metrics using the CodaLab challenge submission(see project page). The object pose annotations for the test and train set are provided along with the dataset.","description_withheld":null,"homepage":"https://www.tugraz.at/institute/icg/research/team-lepetit/research-projects/hand-object-3d-pose-annotation/","introduced_date":"2019-07-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/ho-3d-a-multi-user-multi-object-dataset-for","title":"HOnnotate: A method for 3D Annotation of Hand and Object Poses","first_author":"Shreyas Hampali","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"name":"3D Hand Pose Estimation","url":"/task/3d-hand-pose-estimation","datasets_with_task":"/datasets/task/3d-hand-pose-estimation"},{"name":"3D Pose Estimation","url":"/task/3d-pose-estimation","datasets_with_task":"/datasets/task/3d-pose-estimation"},{"name":"3D Canonical Hand Pose Estimation","url":"/task/3d-canonical-hand-pose-estimation","datasets_with_task":"/datasets/task/3d-canonical-hand-pose-estimation"},{"name":"hand-object pose","url":"/task/hand-object-pose","datasets_with_task":"/datasets/task/hand-object-pose"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HO-3D v2"],"data_loaders":[],"num_papers_in_archive":36,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-hand-pose-estimation-on-ho-3d","task":"3D Hand Pose Estimation","dataset_variant":"HO-3D v2","rows":24,"metrics":["PA-MPJPE (mm)","PA-MPVPE","F@5mm","F@15mm","AUC_J","AUC_V"],"first_row_in_archive_order":{"model":"ExtPose (T=16)","paper":"/paper/extpose-robust-and-coherent-pose-estimation","metrics":{"AUC_J":"0.863","AUC_V":"0.856","F@15mm":"0.991","F@5mm":"0.667","PA-MPJPE (mm)":"6.9","PA-MPVPE":"7.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/hand-object-pose-on-ho-3d","task":"hand-object pose","dataset_variant":"HO-3D v2","rows":9,"metrics":["ST-MPJPE","Average MPJPE (mm)","PA-MPJPE","OME","ADD-S"],"first_row_in_archive_order":{"model":"HOISDF","paper":"/paper/hoisdf-constraining-3d-hand-object-pose","metrics":{"ADD-S":"14.4","Average MPJPE (mm)":"19.0","OME":"35.5","PA-MPJPE":"9.2","ST-MPJPE":"18.3"},"code_links":[{"title":"amathislab/hoisdf","url":"https://github.com/amathislab/hoisdf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/extpose-robust-and-coherent-pose-estimation","title":"ExtPose: Robust and Coherent Pose Estimation by Extending ViTs","date":"2025-06-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hamba-single-view-3d-hand-reconstruction-with","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","date":"2024-07-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/handbooster-boosting-3d-hand-mesh","title":"HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions","date":"2024-03-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":10,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/3d-hand-reconstruction-via-aggregating-intra","title":"3D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenario","date":"2024-03-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hoisdf-constraining-3d-hand-object-pose","title":"HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields","date":"2024-02-26","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":16,"samples_unverified":7,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reconstructing-hands-in-3d-with-transformers","title":"Reconstructing Hands in 3D with Transformers","date":"2023-12-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-probabilistic-attention-model-with","title":"A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image","date":"2023-04-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/harmonious-feature-learning-for-interactive","title":"Harmonious Feature Learning for Interactive Hand-Object Pose Estimation","date":"2023-01-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/h2onet-hand-occlusion-and-orientation-aware","title":"H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interacting-hand-object-pose-estimation-via","title":"Interacting Hand-Object Pose Estimation via Dense Mutual Attention","date":"2022-11-16","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/collaborative-learning-for-hand-and-object","title":"Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution","date":"2022-04-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/handoccnet-occlusion-robust-3d-hand-mesh","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","date":"2022-03-28","rows_on_this_dataset":1,"code_links":0,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mobrecon-mobile-friendly-hand-mesh","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","date":"2021-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":2,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/artiboost-boosting-articulated-3d-hand-object","title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","date":"2021-09-12","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/towards-unconstrained-joint-hand-object","title":"Towards unconstrained joint hand-object reconstruction from RGB videos","date":"2021-08-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-3d-hand-object-poses","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","date":"2021-06-09","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/handsformer-keypoint-transformer-for","title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","date":"2021-04-29","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/model-based-3d-hand-reconstruction-via-self","title":"Model-based 3D Hand Reconstruction via Self-Supervised Learning","date":"2021-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sr-affine-high-quality-3d-hand-model","title":"I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling","date":"2021-02-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/end-to-end-human-pose-and-mesh-reconstruction","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","date":"2020-12-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pose2mesh-graph-convolutional-network-for-3d","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","date":"2020-08-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/i2l-meshnet-image-to-lixel-prediction-network-1","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","date":"2020-08-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/leveraging-photometric-consistency-over-time","title":"Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction","date":"2020-04-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/learning-joint-reconstruction-of-hands-and","title":"Learning joint reconstruction of hands and manipulated objects","date":"2019-04-11","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":9,"samples_harvested":84,"samples_ran":50,"samples_unverified":34,"pointer_only_for_licence":49,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}