VisibilitySplat: Ray-Traced Occlusion for Relighting with 3D Gaussian Splatting

We address inverse rendering with 3D Gaussian Splatting (3DGS) by introducing explicit visibility modeling for relighting as well as material and light decomposition. Our approach augments the standard rasterized 3DGS pipeline with an auxiliary, BVH-accelerated, point-based ray tracer that computes transmittance-weighted occlusion for Gaussian primitives. The ray tracer is queried sparsely within the inverse rendering objectives, while the original 3DGS loop is retained for training efficiency, interactive visualization, and tooling compatibility. Shading follows a physically based formulation with a principled microfacet BRDF and low-resolution HDR environment maps. We evaluate our method on the TensoIR synthetic dataset against NeRF-, tensor-, and GS-based baselines. The results show competitive performance and improvements over several earlier baselines for novel-view synthesis, albedo reconstruction, and relighting. Ablations indicate that explicit visibility modeling is an important contributor to relighting and material-illumination disentanglement, while pure PBR supervision can favor appearance fitting in NVS. Overall, the findings suggest that sparse, point-based visibility queries effectively complement rasterized splatting for inverse rendering while preserving the practical advantages of the 3DGS ecosystem.