HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915688998764544 |
|---|---|
| author | Dong, Yilan Wang, Wenqing Wang, Qing Yang, Jiahao Liu, Haohe Zhu, Xiatuan Slabaugh, Gregory Yuan, Shanxin |
| author_facet | Dong, Yilan Wang, Wenqing Wang, Qing Yang, Jiahao Liu, Haohe Zhu, Xiatuan Slabaugh, Gregory Yuan, Shanxin |
| contents | Creating animatable hand avatars from multi-view images requires modeling complex articulations and maintaining structural consistency across poses in real time. We present HandSCS, a structure-guided 3D Gaussian Splatting framework for high-fidelity hand animation. Unlike existing approaches that condition all Gaussians on the same global pose parameters, which are inadequate for highly articulated hands, HandSCS equips each Gaussian with explicit structural guidance from both intra-pose and inter-pose perspectives. To establish intra-pose structural guidance, we introduce a Structural Coordinate Space (SCS), which bridges the gap between sparse bones and dense Gaussians through hybrid static-dynamic coordinate basis and angular-radial descriptors. To improve cross-pose coherence, we further introduce an Inter-pose Consistency Loss that promotes consistent Gaussian attributes under similar articulations. Together, these components achieve high-fidelity results with consistent fine details, even in challenging high-deformation and self-contact regions. Experiments on the InterHand2.6M dataset demonstrate that HandSCS achieves state-of-the-art performance in hand avatar animation, confirming the effectiveness of explicit structural modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14736 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting Dong, Yilan Wang, Wenqing Wang, Qing Yang, Jiahao Liu, Haohe Zhu, Xiatuan Slabaugh, Gregory Yuan, Shanxin Computer Vision and Pattern Recognition Creating animatable hand avatars from multi-view images requires modeling complex articulations and maintaining structural consistency across poses in real time. We present HandSCS, a structure-guided 3D Gaussian Splatting framework for high-fidelity hand animation. Unlike existing approaches that condition all Gaussians on the same global pose parameters, which are inadequate for highly articulated hands, HandSCS equips each Gaussian with explicit structural guidance from both intra-pose and inter-pose perspectives. To establish intra-pose structural guidance, we introduce a Structural Coordinate Space (SCS), which bridges the gap between sparse bones and dense Gaussians through hybrid static-dynamic coordinate basis and angular-radial descriptors. To improve cross-pose coherence, we further introduce an Inter-pose Consistency Loss that promotes consistent Gaussian attributes under similar articulations. Together, these components achieve high-fidelity results with consistent fine details, even in challenging high-deformation and self-contact regions. Experiments on the InterHand2.6M dataset demonstrate that HandSCS achieves state-of-the-art performance in hand avatar animation, confirming the effectiveness of explicit structural modeling. |
| title | HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.14736 |