# HO-3D_v3: Improving the Accuracy of Hand-Object Annotations of the HO-3D Dataset

arXiv: https://arxiv.org/abs/2107.00887 · HTML: https://mlsanity.com/paper/2107.00887/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 3 references that are in the map.
- First posted on arXiv 2 Jul 2021.

## Built on by (most cited first, 26 of 26)

- [ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis](https://mlsanity.com/paper/2109.05488/) (2021)
- [Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba](https://mlsanity.com/paper/2407.09646/) (2024)
- [A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image](https://mlsanity.com/paper/2304.14299/) (2023)
- [HMP: Hand Motion Priors for Pose and Shape Estimation from Video](https://mlsanity.com/paper/2312.16737/) (2023)
- [ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping](https://mlsanity.com/paper/2412.16212/) (2024)
- [SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction](https://mlsanity.com/paper/2309.10748/) (2023)
- [HORT: Monocular Hand-held Objects Reconstruction with Transformers](https://mlsanity.com/paper/2503.21313/) (2025)
- [POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo](https://mlsanity.com/paper/2304.04038/) (2023)
- [Learning Explicit Contact for Implicit Reconstruction of Hand-held Objects from Monocular Images](https://mlsanity.com/paper/2305.20089/) (2023)
- [HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image](https://mlsanity.com/paper/2309.07891/) (2023)
- [UV-Based 3D Hand-Object Reconstruction with Grasp Optimization](https://mlsanity.com/paper/2211.13429/) (2022)
- [ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning](https://mlsanity.com/paper/2512.22854/) (2025)
- [Multi-view Hand Reconstruction with a Point-Embedded Transformer](https://mlsanity.com/paper/2408.10581/) (2024)
- [Weakly-Supervised 3D Hand Reconstruction with Knowledge Prior and Uncertainty Guidance](https://mlsanity.com/paper/2407.12307/) (2024)
- [HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Images](https://mlsanity.com/paper/2403.07912/) (2024)
- [MLPHand: Real Time Multi-View 3D Hand Mesh Reconstruction via MLP Modeling](https://mlsanity.com/paper/2406.16137/) (2024)
- [Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions](https://mlsanity.com/paper/2604.12929/) (2026)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?](https://mlsanity.com/paper/2211.00110/) (2022)
- [Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation](https://mlsanity.com/paper/2504.01298/) (2025)
- [Person Identification from Egocentric Human-Object Interactions using 3D Hand Pose](https://mlsanity.com/paper/2509.16557/) (2025)
- [SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation](https://mlsanity.com/paper/2510.16396/) (2025)
- [UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation](https://mlsanity.com/paper/2605.17742/) (2026)
- [EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision](https://mlsanity.com/paper/2608.13014/) (2026)
- [StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images](https://mlsanity.com/paper/2610.09195/) (2026)
- [Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery](https://mlsanity.com/paper/2610.10512/) (2026)

## Abstract (arXiv)

HO-3D is a dataset providing image sequences of various hand-object interaction scenarios annotated with the 3D pose of the hand and the object and was originally introduced as HO-3D_v2. The annotations were obtained automatically using an optimization method, 'HOnnotate', introduced in the original paper. HO-3D_v3 provides more accurate annotations for both the hand and object poses thus resulting in better estimates of contact regions between the hand and the object. In this report, we elaborate on the improvements to the HOnnotate method and provide evaluations to compare the accuracy of HO-3D_v2 and HO-3D_v3. HO-3D_v3 results in 4mm higher accuracy compared to HO-3D_v2 for hand poses while exhibiting higher contact regions with the object surface.