Research map / 3D vision / 3D generation
LightSwitch: Multi-view Relighting with Material-guided Diffusion
Yehonathan Litman, Fernando De la Torre, Shubham Tulsiani
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 inferred material maps as conditioning (ablation) | LightSwitch · BlenderVault 2D relighting | PSNR: 25.27 -> 26.01 | Improved |
| add multi-view attention (ablation) | LightSwitch · BlenderVault 2D relighting | PSNR: 24.59 -> 26.01 | Improved |
| use ground-truth materials instead of inferred | LightSwitch · BlenderVault 2D relighting | PSNR: 26.01 -> 28.29 | Improved |
| multi-view model vs single-view baseline Neural Gaffer on scene-level rescaling | Neural Gaffer · BlenderVault 2D relighting (SLR) | PSNR: 24.08 -> 25.86 | Improved |
| distribute denoising over 8 GPUs | LightSwitch · NeRF-Synthetic runtime | Runtime (minutes): 14 -> ~2 | Improved |
| LightSwitch vs Mitsuba+NeuS on real Objects With Lighting | Mitsuba+NeuS · Objects With Lighting | PSNR: 26.24 -> 25.43 | Hurt |
| LightSwitch vs inverse rendering on NeRF-Synthetic Materials object | NVDiffrecMC · NeRF-Synthetic Materials | PSNR: 25.37 -> 22.08 | Hurt |
| LightSwitch vs inverse rendering on Stanford-ORB | Neural-PBIR · Stanford-ORB | PSNR-H: 26.01 -> 25.03 | Hurt |
Later papers that compared with this method
3 later accepted papers report LightSwitch as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- LumiTokens: 3D Relighting via Token-Space Lighting Transformation (ECCV 2026 · better on 6 of 7 shared results)
- MatSpray: Fusing 2D Material World Knowledge on 3D Geometry (CVPR 2026 · better on 3 of 3 shared results)
- DANTE-W: Diffuse Albedo Neural Texturing in the Wild (ECCV 2026 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- IllumiNeRF — IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024) · better on 0 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
- Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion (CVPR 2025 · similarity 0.91)
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting (NeurIPS 2025 · similarity 0.91)
- ReCap: Better Gaussian Relighting with Cross-Environment Captures (CVPR 2025 · similarity 0.90)
- Neural Gaffer: Relighting Any Object via Diffusion (NeurIPS 2024 · similarity 0.90)
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.90)
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · similarity 0.90)
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.
