Research map / 3D vision / Depth and stereo
Editable Indoor Lighting Estimation
Henrique Weber, Mathieu Garon, Jean-François Lalonde
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 |
|---|---|---|---|
| provide estimated layout as input to the layout network (ablation) | Ours · Laval Indoor test (2,240 images) | FID: 88.68 -> 89.58 | No clear effect |
| add parametric light and layout to texture network input beyond RGB crop (ablation) | Ours · Laval Indoor test (2,240 images) | FID: 167.39 -> 89.57 | Improved |
| add layout to texture network input given RGB crop and light (ablation) | Ours · Laval Indoor test (2,240 images) | FID: 97.13 -> 89.57 | Improved |
| add parametric light to texture network input given RGB crop and layout (ablation) | Ours · Laval Indoor test (2,240 images) | FID: 151.04 -> 89.57 | Improved |
| add layout alone to RGB crop (ablation) | Ours · Laval Indoor test (2,240 images) | FID: 167.39 -> 151.04 | Improved |
| add parametric light alone to RGB crop (ablation) | Ours · Laval Indoor test (2,240 images) | FID: 167.39 -> 97.13 | Improved |
| use editable 1-light parametric plus texture representation instead of 3 estimated lights | Gardner'19 · Laval Indoor test (2,240 images) | RMSE: 0.508 -> 0.209 | Improved |
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.
- EMLight — EMLight: Lighting Estimation via Spherical Distribution Approximation (AAAI 2021) · better on 4 of 5 shared results
- Lighthouse — Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination (CVPR 2020) · better on 4 of 4 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
- Physically-Based Editing of Indoor Scene Lighting from a Single Image (ECCV 2022 · similarity 0.91)
- Fast Spatially-Varying Indoor Lighting Estimation (CVPR 2019 · similarity 0.90)
- Deep Parametric Indoor Lighting Estimation (ICCV 2019 · similarity 0.90)
- LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation (CVPR 2024 · similarity 0.89)
- ScribbleLight: Single Image Indoor Relighting with Scribbles (CVPR 2025 · similarity 0.87)
- Do Image Editing Models Understand Lighting? (NeurIPS 2026 · 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.
