Fast and Accurate Hand Estimation in Pixels, Interaction and World Space
cs.CV, cs.RO
Submitted: 2026-11-05
Updated: 2026-11-05
Comments: 10 pages of main text plus 15 pages of supplementary material; 5 figures; 12 tables; code available at https://github.com/noahcao/FAH
Code: https://github.com/noahcao/FAH
Project page: https://jyuntins.github.io/Contact4D
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MHR: Momentum Human Rig
- AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
- MediaPipe Hands: On-device Real-time Hand Tracking
- RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
- RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation
- DINOv3
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs