Research map / 3D vision / Gaussian splatting
Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
Francesco Di Sario, Daniel Rebain, Dor Verbin, Marco Grangetto, Andrea Tagliasacchi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace SH with Spherical Voronoi for view-dependent color (ablation) | Beta-Splatting · Mip-NeRF360 | PSNR: 28.09 -> 28.57 | Improved |
| replace SH with Spherical Voronoi for view-dependent color (ablation) | Beta-Splatting · DeepBlending | PSNR: 29.80 -> 30.48 | Improved |
| replace SH with Spherical Voronoi for view-dependent color (ablation) | Beta-Splatting · NeRF-Synthetic | PSNR: 34.15 -> 34.53 | Improved |
| replace SH with Spherical Voronoi for view-dependent color (ablation) | Beta-Splatting · Tanks&Temples | PSNR: 24.50 -> 24.75 | Improved |
| use SV for light probes instead of SG (ablation) | SV reflection model on 2DGS · Ref-NeRF dataset | PSNR: 34.19 -> 36.09 | Improved |
| use SV for light probes instead of cubemap (ablation) | SV reflection model on 2DGS · Ref-NeRF dataset | PSNR: 34.48 -> 36.09 | Improved |
| explicit SV probes vs Ref-GS MLP decoder | 2DGS reflection model · Ref-Real | PSNR: 23.81 -> 23.91 | No clear effect |
| add SV probes vs Ref-GS on GlossySynthetic | 2DGS reflection model · GlossySynthetic | PSNR: 31.27 -> 31.30 | No clear effect |
| explicit SV probes instead of MLP decoder (Ref-GS) | 2DGS reflection model · Ref-NeRF dataset | PSNR: 35.57 -> 36.09 | Improved |
| reflection modeling vs radiance-only | SV model · efficiency | rendering speed vs 3DGS: 1.00x -> 0.45x | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Ref-GS — Ref-GS: Directional Factorization for 2D Gaussian Splatting (CVPR 2025) · better on 5 of 5 shared results
- Zip-NeRF — Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.88)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · similarity 0.88)
- Ref-GS: Directional Factorization for 2D Gaussian Splatting (CVPR 2025 · similarity 0.87)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.87)
- Geometry Field Splatting with Gaussian Surfels (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
