Datasets › HO-3D v2

HO-3D v2

Introduced by Shreyas Hampali et al. in HOnnotate: A method for 3D Annotation of Hand and Object Poses2 Jul 2019 archive 2025-07-28

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.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
3D Hand Pose Estimation HO-3D v2 ExtPose (T=16) PA-MPJPE (mm) 6.9 ExtPose: Robust and Coherent Pose Estimation by Extending ViTs — 24 Compare
hand-object pose HO-3D v2 HOISDF ST-MPJPE 18.3 HOISDF: Constraining 3D Hand-Object Pose Estimation with... amathislab/hoisdf 9 Compare

Papers archive 2025-07-28

26 shown of 26 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 36. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
ExtPose: Robust and Coherent Pose Estimation by Extending ViTs 0 1 18 Jun 2025 not harvested
WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild 1 1 18 Sep 2024 not harvested
Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba 1 1 12 Jul 2024 ran 7 of 11 samples (4 unverified; 11 pointer-only for licence)
HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions 1 1 27 Mar 2024 ran 10 of 10 samples (0 unverified)
3D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenario 0 1 4 Mar 2024 not harvested
HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields 1 2 26 Feb 2024 ran 16 of 23 samples (7 unverified; 23 pointer-only for licence)
Reconstructing Hands in 3D with Transformers 1 1 8 Dec 2023 ran 0 of 6 samples (6 unverified)
A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image 1 1 27 Apr 2023 not harvested
Harmonious Feature Learning for Interactive Hand-Object Pose Estimation 1 2 1 Jan 2023 not harvested
H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction 1 1 1 Jan 2023 not harvested
Interacting Hand-Object Pose Estimation via Dense Mutual Attention 1 2 16 Nov 2022 ran 1 of 5 samples (4 unverified)
Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution 0 1 27 Apr 2022 not harvested
HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network 0 1 28 Mar 2022 ran 6 of 8 samples (2 unverified; 8 pointer-only for licence)
MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image 1 1 6 Dec 2021 ran 2 of 9 samples (7 unverified)
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis 2 2 12 Sep 2021 not harvested
Towards unconstrained joint hand-object reconstruction from RGB videos 1 2 16 Aug 2021 not harvested
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time 1 2 9 Jun 2021 not harvested
Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation 1 2 29 Apr 2021 not harvested
Model-based 3D Hand Reconstruction via Self-Supervised Learning 1 1 22 Mar 2021 ran 4 of 7 samples (3 unverified; 7 pointer-only for licence)
I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling 0 1 7 Feb 2021 not harvested
End-to-End Human Pose and Mesh Reconstruction with Transformers 1 1 17 Dec 2020 not harvested
Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose 2 1 20 Aug 2020 not harvested
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image 1 1 9 Aug 2020 ran 4 of 5 samples (1 unverified)
Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction 0 1 28 Apr 2020 not harvested
HOnnotate: A method for 3D Annotation of Hand and Object Poses 4 1 2 Jul 2019 not harvested
Learning joint reconstruction of hands and manipulated objects 3 1 11 Apr 2019 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • HO-3D v2

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections