SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian Splatting

2026-04-14

AI Summary

Existing relighting methods based on 3D Gaussian splatting struggle to accurately model the complex light-material interactions of anisotropic metals and translucent materials. This work proposes the first relighting framework within 3D Gaussian splatting that incorporates a four-component physically-based reflectance decomposition, disentangling appearance into diffuse, specular, shadow, and subsurface scattering components. The framework introduces a learnable dipole-based subsurface scattering module, occlusion-aware shadow modeling, and an anisotropic Fresnel reflection model. Through a progressive multi-component joint optimization strategy, the method significantly enhances both physical interpretability and rendering fidelity. Quantitative and perceptual evaluations on the OLAT dataset demonstrate superior relighting quality compared to existing approaches, enabling applications such as controllable lighting editing and interactive relighting.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

We present SSD-GS, a physically-based relighting framework built upon 3D Gaussian Splatting (3DGS) that achieves high-quality reconstruction and photorealistic relighting under novel lighting conditions. In physically-based relighting, accurately modeling light-material interactions is essential for faithful appearance reproduction. However, existing 3DGS-based relighting methods adopt coarse shading decompositions, either modeling only diffuse and specular reflections or relying on neural networks to approximate shadows and scattering. This leads to limited fidelity and poor physical interpretability, particularly for anisotropic metals and translucent materials. To address these limitations, SSD-GS decomposes reflectance into four components: diffuse, specular, shadow, and subsurface scattering. We introduce a learnable dipole-based scattering module for subsurface transport, an occlusion-aware shadow formulation that integrates visibility estimates with a refinement network, and an enhanced specular component with an anisotropic Fresnel-based model. Through progressive integration of all components during training, SSD-GS effectively disentangles lighting and material properties, even for unseen illumination conditions, as demonstrated on the challenging OLAT dataset. Experiments demonstrate superior quantitative and perceptual relighting quality compared to prior methods and pave the way for downstream tasks, including controllable light source editing and interactive scene relighting. The source code is available at: https://github.com/irisfreesiri/SSD-GS.

Problem

• relighting
• 3D Gaussian Splatting
• subsurface scattering
• anisotropic materials
• physically-based rendering

Innovation

• Subsurface Scattering
• Anisotropic Specular
• Occlusion-aware Shadow
• Physically-based Relighting
• 3D Gaussian Splatting