VolS-GS: Relightable Gaussian Splatting with Volumetric Subsurface Scattering

2026-10-02

AI Summary

This study addresses the inherent limitation of 3D Gaussian Splatting in representing non-local illumination effects such as subsurface scattering. To overcome this, we propose a relightable object reconstruction method leveraging One-Light-At-A-Time (OLAT) data. Specifically, our approach utilizes the Gaussian scene space as the computational domain for a differentiable finite-volume transport solver. Rather than relying on conventional local kernels or purely neural network-based modeling, we simulate light propagation within objects through a physics-based solver. A neural network is employed to predict scattering and absorption coefficients, complemented by shadow and specular regularization constraints. Experimental evaluations demonstrate that the proposed method significantly improves rendering quality under novel view and novel lighting conditions across three OLAT benchmarks.

Abstract

We present VolS-GS, a relightable Gaussian splatting framework that reconstructs objects from one-light-at-a-time (OLAT) captures and renders them under novel lighting and viewpoints. Relightable Gaussian Splatting methods typically model appearance independently at each primitive, which makes non-local effects difficult to represent. This limitation is particularly apparent for subsurface scattering, where light entering the object at one location can emerge at another. Rather than modeling this effect solely with a neural network or a local kernel at each primitive, we use the spatial support of the Gaussian scene as the domain of a differentiable finite-volume transport solver, so that light can propagate through the object's interior. A small network predicts scattering and absorption coefficients for each Gaussian, and the solve redistributes incident light through the resulting field. The coefficients are fit to images rather than measured, so the solve supplies a transport-shaped path for aggregating per-primitive appearance, not a measurement of the material. To keep the learned shadow and specular terms from taking over the other components, our shadow term is predicted from visibility together with the transmittances and the scattering the solve produces, and a regularizer suppresses specular highlights in regions the shadow term predicts to be unlit. Experiments on three OLAT benchmarks show that VolS-GS consistently improves relighting quality on held-out lights and views.

Problem

• Relightable Gaussian Splatting
• Subsurface Scattering
• Non-local Effects
• OLAT

Innovation

• Gaussian Splatting
• Subsurface Scattering
• Relighting
• Finite-Volume Transport Solver
• Differentiable Rendering