Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

GRAB: A Dataset of Whole-Body Human Grasping of Objects

GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)

[CVPR 2022 Oral] ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

[CVPR 2022] OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction

This is a repository for GraspXL, which can generate objective-drive grasping motions for 500k+ objects with different dexterous hands.

[ECCV 2022] SAGA: Stochastic Whole-Body Grasping with Contact

AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose (ICCV 2023)

ContactGen: Generative Contact Modeling for Grasp Generation (ICCV 2023)

[CVPR 2024] HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

[WACV 2023] Interacting Hand-Object Pose Estimation via Dense Mutual Attention

[NeurIPS 2022 Spotlight] Hand-Object Interaction Image Generation

Code for the paper "AMEGO: Active Memory from long EGOcentric videos" published at ECCV 2024

Code implementation for paper titled "HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision"

hand-object contact models for ContactPose

SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction (Dataset, Contains proposed top baseline reconstructions with estimated camera poses)

Grasp Generation models on OakInk-Shape dataset

A Python package that provides evaluation and visualization tools for the HOCap dataset