Research map / 3D vision / Gaussian splatting
Radiant Foam: Real-Time Differentiable Ray Tracing
Shrisudhan Govindarajan, Daniel Rebain, Kwang Moo Yi, 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 |
|---|---|---|---|
| add SfM point initialization (ablation) | Radiant Foam · Ablation (Bonsai, Garden, Playground mean) | PSNR: 27.00 -> 29.15 | Improved |
| add densification (with random init) (ablation) | Radiant Foam · Ablation (Bonsai, Garden, Playground mean) | PSNR: 19.36 -> 27.00 | Improved |
| add pruning of non-surface sites (ablation) | Radiant Foam · Ablation (Bonsai, Garden, Playground mean) | PSNR: 29.15 -> 29.15 | No clear effect |
| add quantile regularization loss (ablation) | Radiant Foam · Ablation (Bonsai, Garden, Playground mean) | PSNR: 27.90 -> 29.15 | Improved |
| add pruning of non-surface sites (ablation) | Radiant Foam · Ablation (Bonsai) | PSNR: 32.25 -> 32.15 | No clear effect |
| add quantile regularization loss (ablation) | Radiant Foam · Ablation (Playground) | PSNR: 29.59 -> 29.59 | No clear effect |
| ray tracing Voronoi foam instead of 3DGRT | Radiant Foam · Deep Blending | FPS: 119 -> 301 | Improved |
| ray tracing foam instead of 3DGRT | Radiant Foam · Mip-NeRF 360 | FPS: 78 -> 200 | Improved |
| Radiant Foam vs 3DGS rasterization | Radiant Foam · Mip-NeRF 360 | PSNR: 28.69 -> 28.47 | Hurt |
| Radiant Foam vs 3DGRT on perceptual quality | Radiant Foam · Mip-NeRF 360 | LPIPS: 0.25 -> 0.21 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.
- Mip-Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 1 of 4 shared results
- MipNeRF360 — Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields (CVPR 2022) · better on 0 of 2 shared results
- Plenoxels — Plenoxels: Radiance Fields Without Neural Networks (CVPR 2022) · better on 2 of 2 shared results
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
- Hardware-Rasterized Ray-Based Gaussian Splatting (CVPR 2025 · similarity 0.90)
- 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)
- Subsurface Scattering for Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- Reflective Gaussian Splatting (ICLR 2025 · similarity 0.87)
- SpecTRe-GS: Modeling Highly Specular Surfaces with Reflected Nearby Objects by Tracing Rays in 3D Gaussian Splatting (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.
