UniHands: Unifying Various Wild-Collected Keypoints for Personalized Hand Reconstruction

TL;DR

UniHands introduces a scalable method for creating standardized, personalized hand models from diverse wild-collected keypoints, enhancing hand reconstruction accuracy and integration for various applications.

Contribution

It leverages parametric models MANO and NIMBLE to unify diverse keypoints into a consistent hand representation, improving scalability and versatility.

Findings

Accurately reconstructs hand mesh vertices and keypoints.

Demonstrates high articulation motion capture on benchmark datasets.

Participants prefer UniHands' joint configurations for accuracy and naturalism.

Abstract

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).