GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908469348532224 |
|---|---|
| author | Bai, Haiyang Zhu, Jiaqi Jiang, Songru Huang, Wei Lu, Tao Li, Yuanqi Guo, Jie Fu, Runze Guo, Yanwen Chen, Lijun |
| author_facet | Bai, Haiyang Zhu, Jiaqi Jiang, Songru Huang, Wei Lu, Tao Li, Yuanqi Guo, Jie Fu, Runze Guo, Yanwen Chen, Lijun |
| contents | We propose a 3D Gaussian splatting-based framework for outdoor relighting that leverages intrinsic image decomposition to precisely integrate sunlight, sky radiance, and indirect lighting from unconstrained photo collections. Unlike prior methods that compress the per-image global illumination into a single latent vector, our approach enables simultaneously diverse shading manipulation and the generation of dynamic shadow effects. This is achieved through three key innovations: (1) a residual-based sun visibility extraction method to accurately separate direct sunlight effects, (2) a region-based supervision framework with a structural consistency loss for physically interpretable and coherent illumination decomposition, and (3) a ray-tracing-based technique for realistic shadow simulation. Extensive experiments demonstrate that our framework synthesizes novel views with competitive fidelity against state-of-the-art relighting solutions and produces more natural and multifaceted illumination and shadow effects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20512 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections Bai, Haiyang Zhu, Jiaqi Jiang, Songru Huang, Wei Lu, Tao Li, Yuanqi Guo, Jie Fu, Runze Guo, Yanwen Chen, Lijun Computer Vision and Pattern Recognition We propose a 3D Gaussian splatting-based framework for outdoor relighting that leverages intrinsic image decomposition to precisely integrate sunlight, sky radiance, and indirect lighting from unconstrained photo collections. Unlike prior methods that compress the per-image global illumination into a single latent vector, our approach enables simultaneously diverse shading manipulation and the generation of dynamic shadow effects. This is achieved through three key innovations: (1) a residual-based sun visibility extraction method to accurately separate direct sunlight effects, (2) a region-based supervision framework with a structural consistency loss for physically interpretable and coherent illumination decomposition, and (3) a ray-tracing-based technique for realistic shadow simulation. Extensive experiments demonstrate that our framework synthesizes novel views with competitive fidelity against state-of-the-art relighting solutions and produces more natural and multifaceted illumination and shadow effects. |
| title | GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.20512 |