mlsanityData to 14 Oct 2026

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

arXiv 2610.19847 ↗First posted 14 Oct 2026cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

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 a sparse visibility oracle that estimates transmittance-weighted occlusion for Gaussian primitives from sampled lighting directions. This oracle is implemented using a point-based ray tracer accelerated by a bounding volume hierarchy (BVH) and 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 rendering (PBR) formulation with a principled microfacet bidirectional reflectance distribution function (BRDF) and low-resolution high-dynamic-range (HDR) environment maps. We evaluate our method on the TensoIR synthetic dataset against baselines based on neural radiance fields (NeRFs), tensor representations, and 3DGS. The results show competitive performance and improvements over several earlier baselines for novel-view synthesis (NVS), 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

30 of 42 references.

References · 30

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  9. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  10. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  11. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  12. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
18 more
  1. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  2. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
  3. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
  4. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  5. 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
  6. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 232
  7. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 224
  8. 2022Modeling Indirect Illumination for Inverse Renderingcited by 168
  9. 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 142
  10. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 139
  11. 2023GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorizationcited by 87
  12. 2023NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimationcited by 74
  13. 2023ENVIDR: Implicit Differentiable Renderer with Neural Environment Lightingcited by 65
  14. 2024GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Renderingcited by 42
  15. 2024Reflective Gaussian Splattingcited by 42
  16. 2024DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shadingcited by 41
  17. 2024RNG: Relightable Neural Gaussianscited by 16
  18. 2024NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Renderingcited by 8

Built on by

Not cited yet.