2024/11/18 by Menghe Zhang, Zhang, Menghe, Yangwen Liang +6
Arts and Humanities · Engineering · #Anatomy and Medical Technology #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Forensic Anthropology and Bioarchaeology Studies #Human-Computer Interaction (cs.HC)
paper · pdf · doi:10.48550/arxiv.2411.11845
openalex publication_date 2024/11/18 · openalex created_date 2024/11/21 · openalex updated_date 2026/07/28
Accurate hand motion capture and standardized 3D representation are essential for various hand-related tasks. Collecting keypoints-only data, while efficient and cost-effective, results in low-fidelity representations and lacks surface information. Furthermore, data inconsistencies across sources challenge their integration and use. We present UniHands, a novel method for creating standardized yet personalized hand models from wild-collected keypoints from diverse sources. Unlike existing neural implicit representation methods, UniHands uses the widely-adopted parametric models MANO and NIMBLE, providing a more scalable and versatile solution. It also derives unified hand joints from the meshes, which facilitates seamless integration into various hand-related tasks. Experiments on the FreiHAND and InterHand2.6M datasets demonstrate its ability to precisely reconstruct hand mesh vertices and keypoints, effectively capturing high-degree articulation motions. Empirical studies involving nine participants show a clear preference for our unified joints over existing configurations for accuracy and naturalism (p-value 0.016).