Research map / 3D vision / 3D generation
Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting
Chenjian Gao, Linning Xu, Tianfan Xue
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 illumination palette (distillation stage) (ablation) | Lume-Palette · Synthetic scenes ablation | PSNR: 22.748 -> 24.453 | Improved |
| add illumination palette (distillation stage) (ablation) | Lume-Palette · Synthetic scenes ablation | LPIPS: 0.128 -> 0.126 | Improved |
| add illumination palette (distillation stage) (ablation) | Lume-Palette · Synthetic scenes ablation | SSIM: 0.854 -> 0.872 | Improved |
| add multi-view awareness (asymmetric conditioning) (ablation) | Lume-Palette · Synthetic scenes ablation | PSNR: 23.618 -> 24.453 | Improved |
| add multi-view awareness (asymmetric conditioning) (ablation) | Lume-Palette · Synthetic scenes ablation | SSIM: 0.864 -> 0.872 | Improved |
| add multi-view awareness (asymmetric conditioning) (ablation) | Lume-Palette · Synthetic scenes ablation | LPIPS: 0.131 -> 0.126 | Improved |
| add both palette and multi-view awareness (ablation) | Lume-Palette · Synthetic scenes ablation | PSNR: 21.973 -> 24.453 | Improved |
| add both palette and multi-view awareness (ablation) | Lume-Palette · Synthetic scenes ablation | LPIPS: 0.140 -> 0.126 | Improved |
| Lume-Palette vs best baseline on multi-view MSE | Lume-Palette · Synthetic scenes relighting | MV MSE: 0.0159 -> 0.0090 | Improved |
Closest papers by meaning
- LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting (CVPR 2025 · similarity 0.92)
- ScribbleLight: Single Image Indoor Relighting with Scribbles (CVPR 2025 · similarity 0.90)
- UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting (NeurIPS 2025 · similarity 0.88)
- SyncLight: Single-Edit Multi-View Relighting (NeurIPS 2026 · similarity 0.88)
- SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces (CVPR 2025 · similarity 0.88)
- Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset (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.
