Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915629004488704 |
|---|---|
| author | Sun, Yipengjing Zhang, Shengping Wang, Chenyang Zheng, Shunyuan Li, Zonglin Ji, Xiangyang |
| author_facet | Sun, Yipengjing Zhang, Shengping Wang, Chenyang Zheng, Shunyuan Li, Zonglin Ji, Xiangyang |
| contents | We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. Unlike existing methods that rely on per-character optimization or ignore physical constraints, GRGS adopts a feed-forward, fully supervised strategy projecting geometry, material, and illumination cues from multi-view 2D observations into 3D Gaussian representations. To recover accurate geometry under diverse lighting conditions, we introduce a Lighting-robust Geometry Refinement (LGR) module trained on synthetically relit data to predict precise depth and surface normals. Based on the high-quality geometry, a Physically Grounded Neural Rendering (PGNR) module is further proposed to integrate neural prediction with physics-based shading, supporting editable relighting with shadows and indirect illumination. Moreover, we design a 2D-to-3D projection training scheme leveraging differentiable supervision from ambient occlusion, direct, and indirect lighting maps, alleviating the computational cost of ray tracing. Extensive experiments demonstrate that GRGS achieves superior visual quality, geometric consistency, and generalization across characters and lighting conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21502 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis Sun, Yipengjing Zhang, Shengping Wang, Chenyang Zheng, Shunyuan Li, Zonglin Ji, Xiangyang Computer Vision and Pattern Recognition We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. Unlike existing methods that rely on per-character optimization or ignore physical constraints, GRGS adopts a feed-forward, fully supervised strategy projecting geometry, material, and illumination cues from multi-view 2D observations into 3D Gaussian representations. To recover accurate geometry under diverse lighting conditions, we introduce a Lighting-robust Geometry Refinement (LGR) module trained on synthetically relit data to predict precise depth and surface normals. Based on the high-quality geometry, a Physically Grounded Neural Rendering (PGNR) module is further proposed to integrate neural prediction with physics-based shading, supporting editable relighting with shadows and indirect illumination. Moreover, we design a 2D-to-3D projection training scheme leveraging differentiable supervision from ambient occlusion, direct, and indirect lighting maps, alleviating the computational cost of ray tracing. Extensive experiments demonstrate that GRGS achieves superior visual quality, geometric consistency, and generalization across characters and lighting conditions. |
| title | Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.21502 |