Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.19088 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913673123987456 |
|---|---|
| author | Sun, Zhoutao Shen, Xukun Hu, Yong Zhong, Yuyou Zhou, Xueyang |
| author_facet | Sun, Zhoutao Shen, Xukun Hu, Yong Zhong, Yuyou Zhou, Xueyang |
| contents | Since hands are the primary interface in daily interactions, modeling high-quality digital human hands and rendering realistic images is a critical research problem. Furthermore, considering the requirements of interactive and rendering applications, it is essential to achieve real-time rendering and driveability of the digital model without compromising rendering quality. Thus, we propose Jointly 3D Gaussian Hand (JGHand), a novel joint-driven 3D Gaussian Splatting (3DGS)-based hand representation that renders high-fidelity hand images in real-time for various poses and characters. Distinct from existing articulated neural rendering techniques, we introduce a differentiable process for spatial transformations based on 3D key points. This process supports deformations from the canonical template to a mesh with arbitrary bone lengths and poses. Additionally, we propose a real-time shadow simulation method based on per-pixel depth to simulate self-occlusion shadows caused by finger movements. Finally, we embed the hand prior and propose an animatable 3DGS representation of the hand driven solely by 3D key points. We validate the effectiveness of each component of our approach through comprehensive ablation studies. Experimental results on public datasets demonstrate that JGHand achieves real-time rendering speeds with enhanced quality, surpassing state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19088 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JGHand: Joint-Driven Animatable Hand Avater via 3D Gaussian Splatting Sun, Zhoutao Shen, Xukun Hu, Yong Zhong, Yuyou Zhou, Xueyang Computer Vision and Pattern Recognition Since hands are the primary interface in daily interactions, modeling high-quality digital human hands and rendering realistic images is a critical research problem. Furthermore, considering the requirements of interactive and rendering applications, it is essential to achieve real-time rendering and driveability of the digital model without compromising rendering quality. Thus, we propose Jointly 3D Gaussian Hand (JGHand), a novel joint-driven 3D Gaussian Splatting (3DGS)-based hand representation that renders high-fidelity hand images in real-time for various poses and characters. Distinct from existing articulated neural rendering techniques, we introduce a differentiable process for spatial transformations based on 3D key points. This process supports deformations from the canonical template to a mesh with arbitrary bone lengths and poses. Additionally, we propose a real-time shadow simulation method based on per-pixel depth to simulate self-occlusion shadows caused by finger movements. Finally, we embed the hand prior and propose an animatable 3DGS representation of the hand driven solely by 3D key points. We validate the effectiveness of each component of our approach through comprehensive ablation studies. Experimental results on public datasets demonstrate that JGHand achieves real-time rendering speeds with enhanced quality, surpassing state-of-the-art methods. |
| title | JGHand: Joint-Driven Animatable Hand Avater via 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.19088 |