Research map / 3D vision / Depth and stereo
Fast Spatially-Varying Indoor Lighting Estimation
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 |
|---|---|---|---|
| Use spatially-varying local and global masked image features instead of a single global estimate | Indoor lighting estimation · Real indoor light probes | RMSE: 0.081 ± 0.015 -> 0.049 ± 0.006 (Global); 0.072 ± 0.013 -> 0.049 ± 0.006 (Local) | Helped |
| Use spatially-varying local and global masked image features instead of a single global estimate | Indoor lighting estimation · Real indoor light probes | user-study confusion: 31.0% -> 35.8% (Global); 28.0% -> 35.8% (Local) | Helped |
| Add domain adaptation loss (ablation) | Indoor lighting estimator · Real indoor light probes | RMSE: 0.051 ± 0.011 -> 0.049 ± 0.006 | Helped |
| Add domain adaptation loss (ablation) | Indoor lighting estimator · Real indoor light probes | siRMSE: 0.072 ± 0.009 -> 0.062 ± 0.005 | Helped |
| Combine local patch features with global features and a coordinate mask (ablation) | Lighting network · Synthetic test set | MAE, SH degree 0: 0.698 -> 0.520 | Helped |
| Combine local patch features with global features and a coordinate mask (ablation) | Lighting network · Synthetic test set | MAE, SH degree 1: 0.451 -> 0.379 | Helped |
| Combine local patch features with global features and a coordinate mask (ablation) | Lighting network · Synthetic test set | MAE, SH degrees 2–5: 0.182 -> 0.159 | Helped |
| Add low-frequency probe depth prediction loss (ablation) | Lighting network · Synthetic test set | MAE, SH degree 1: 0.379 -> 0.341 | Helped |
| Add low-frequency probe depth prediction loss (ablation) | Lighting network · Synthetic test set | MAE, SH degree 0: 0.520 -> 0.511 | No clear effect |
| Add albedo and shading decomposition losses (ablation) | Lighting network · Synthetic test set | MAE, SH degree 0: 0.520 -> 0.472 | Helped |
| Add albedo and shading decomposition losses (ablation) | Lighting network · Synthetic test set | MAE, SH degree 1: 0.379 -> 0.372 | No clear effect |
| Add albedo and shading decomposition losses (ablation) | Lighting network · Synthetic test set | MAE, SH degrees 2–5: 0.159 -> 0.166 | Hurt |
Closest papers by meaning
- LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation (CVPR 2024 · similarity 0.90)
- ScribbleLight: Single Image Indoor Relighting with Scribbles (CVPR 2025 · similarity 0.85)
- LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting (CVPR 2025 · similarity 0.84)
- LuxDiT: Lighting Estimation with Video Diffusion Transformer (NeurIPS 2025 · similarity 0.83)
- SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation (NeurIPS 2024 · similarity 0.83)
- Do Image Editing Models Understand Lighting? (NeurIPS 2026 · similarity 0.82)
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.