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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Menghe, Kim, Joonyeoup, Liang, Yangwen, Wang, Shuangquan, Song, Kee-Bong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917840676716544
author Zhang, Menghe
Kim, Joonyeoup
Liang, Yangwen
Wang, Shuangquan
Song, Kee-Bong
author_facet Zhang, Menghe
Kim, Joonyeoup
Liang, Yangwen
Wang, Shuangquan
Song, Kee-Bong
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2411_11845
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UniHands: Unifying Various Wild-Collected Keypoints for Personalized Hand Reconstruction
Zhang, Menghe
Kim, Joonyeoup
Liang, Yangwen
Wang, Shuangquan
Song, Kee-Bong
Computer Vision and Pattern Recognition
Human-Computer Interaction
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).
title UniHands: Unifying Various Wild-Collected Keypoints for Personalized Hand Reconstruction
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2411.11845