Subsurface Scattering for 3D Gaussian Splatting
–Neural Information Processing Systems
While 3D Gaussians efficiently approximate an object's surface, they fail to capture the volumetric properties of subsurface scattering. We propose a framework for optimizing an object's shape together with the radiance transfer field given multiview OLAT (one light at a time) data. Our method decomposes the scene into an explicit surface represented as 3D Gaussians, with a spatially varying BRDF, and an implicit volumetric representation of the scattering component. A learned incident light field accounts for shadowing.
Neural Information Processing Systems
Mar-27-2025, 11:22:09 GMT
- Country:
- Europe (0.46)
- North America > United States
- Oklahoma > Beaver County (0.25)
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Information Technology (0.67)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Vision (1.00)
- Graphics (1.00)
- Artificial Intelligence
- Information Technology