Research map / 3D vision / Depth and stereo
Neural Illumination: Lighting Prediction for Indoor Environments
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| decompose the prediction into supervised geometry, warping, completion, and LDR-to-HDR modules (ablation) | Neural Illumination · Matterport3D test | ℓ2: 0.319 -> 0.280 | Helped |
| estimate geometry and use it to warp the image to the target locale (ablation) | Neural Illumination · Matterport3D test | ℓ2: 0.280 -> 0.269 | Helped |
| use oracle warped HDR instead of predicted LDR and geometry (ablation) | Neural Illumination · Matterport3D test | ℓ2: 0.280 -> 0.212 | Helped |
| add adversarial loss to ℓ2 loss (ablation) | HDR+D→HDR · Matterport3D test | ℓ2 (log): 0.116 -> 0.224 | Hurt |
| add adversarial loss to ℓ2 loss (ablation) | HDR+D→HDR · Matterport3D test | ℓ2: 0.235 -> 0.275 | Hurt |
| add adversarial loss to ℓ2 loss (ablation) | HDR+D→HDR · Matterport3D test | diffuse: 0.691 -> 0.713 | Hurt |
| add diffuse convolution loss alongside ℓ2 and adversarial losses (ablation) | HDR+D→HDR · Matterport3D test | ℓ2: 0.275 -> 0.212 | Helped |
| add diffuse convolution loss alongside ℓ2 and adversarial losses (ablation) | HDR+D→HDR · Matterport3D test | diffuse: 0.713 -> 0.619 | Helped |
| predict illumination directly from the image without geometry-conditioned spatial alignment | Neural Illumination · Matterport3D test | ℓ2 (log): 0.229 -> 0.202 | Helped |
Closest papers by meaning
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 2024 · similarity 0.87)
- LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation (CVPR 2024 · similarity 0.87)
- ROGR: Relightable 3D Objects using Generative Relighting (NeurIPS 2025 · similarity 0.87)
- SpecNeRF: Gaussian Directional Encoding for Specular Reflections (CVPR 2024 · similarity 0.87)
- LuxDiT: Lighting Estimation with Video Diffusion Transformer (NeurIPS 2025 · similarity 0.87)
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting (NeurIPS 2025 · similarity 0.86)
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.