UniHands: Unifying Various Wild-Collected Keypoints for Personalized Hand Reconstruction
This work addresses the challenge of integrating inconsistent hand keypoint data for applications in hand motion capture and 3D representation, offering a scalable solution but is incremental in its approach.
The paper tackles the problem of creating standardized, personalized hand models from diverse, low-fidelity keypoint data by introducing UniHands, which uses parametric models to reconstruct hand meshes and unify joints, achieving precise reconstruction and user preference over existing configurations with a p-value of 0.016.
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).