AI RESEARCH
SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian Splatting
arXiv CS.CV
•
ArXi:2604.13333v1 Announce Type: new 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.