facebookresearch / diffh2oLinks
We introduce DiffH2O, a diffusion-based framework to synthesize dexterous hand-object interactions. DiffH2O generates realistic hand-object motion from natural language, generalizes to unseen objects at test time and enables fine-grained control over the motion with detailed textual descriptions.
☆31Updated 2 months ago
Alternatives and similar repositories for diffh2o
Users that are interested in diffh2o are comparing it to the libraries listed below
Sorting:
- Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction☆114Updated 11 months ago
- Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions☆232Updated last month
- [CVPR2025] EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild☆92Updated 2 weeks ago
- ContactGen: Generative Contact Modeling for Grasp Generation (ICCV 2023)☆80Updated 2 years ago
- Physically Plausible Full-Body Hand-Object Interaction Synthesis☆59Updated 2 years ago
- MCC-HO☆53Updated last year
- [CVPR 2024] Official repository of paper "I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions".☆76Updated 3 weeks ago
- [ECCV 2024] Official Implementation of the paper "HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects"☆72Updated 10 months ago
- This is the implementation of CVPR 2025 paper "BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated O…☆37Updated 6 months ago
- Implementation of "MEGA: Masked Generative Autoencoder for Human Mesh Recovery" - CVPR 2025 (Oral)☆34Updated 10 months ago
- [CVPR 2024] Generating Human Motion in 3D Scenes from Text Descriptions☆100Updated last year
- DNO: Optimizing Diffusion Noise Can Serve As Universal Motion Priors☆160Updated last week
- Official implementation of TeSMo, a method for text-controlled scene-aware motion generation, from the ECCV 2024 paper: "Generating Human…☆77Updated last year
- "IMoS: Intent-Driven Fullbody Motion Synthesis for Human-Object Interaction". Proceeding of EUROGRAPHICS 2023.☆104Updated 2 years ago
- This is the code repository for the paper: Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Inte…☆36Updated last year
- This is the official repository of SIGGRAPH Asia 2024 Paper: Autonomous Character-Scene Interaction Synthesis from Text Instruction☆57Updated 6 months ago
- This repository is for fitting mocap data into SMPL-X parameters in [CVPR 2024]"Inter-X: Towards Versatile Human-Human Interaction Analys…☆43Updated last year
- [CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models☆123Updated last month
- ☆51Updated 9 months ago
- HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models, arXiv 2023☆157Updated 2 months ago
- ☆31Updated last month
- Official Implementation of the Paper: Object Motion Guided Human Motion Synthesis (SIGGRAPH Asia 2023 (TOG))☆241Updated 6 months ago
- A pytorch implementation of paper "Motion Flow Matching for Human Motion Synthesis and Editing"☆47Updated last year
- 🔥(CVPR 2025 Highlight) Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera☆195Updated 2 months ago
- [CVPR 2024] Official implementation of the paper "ReGenNet: Towards Human Action-Reaction Synthesis"☆66Updated last year
- ☆28Updated 2 months ago
- [ICLR'24] GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion☆116Updated last year
- Unify text-motion datasets (like BABEL, HumanML3D, KIT-ML) into a common motion-text representation.☆55Updated 2 years ago
- Author's implementation of the paper Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera (C…☆68Updated last year
- This is the official repository of CVPR 2025 Paper: Dynamic Motion Blending for Versatile Motion Editing.☆45Updated 10 months ago