Research map / 3D vision / Depth and stereo
Deep Parametric Indoor Lighting Estimation
Marc-Andre Gardner, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Christian Gagne, Jean-Francois 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 |
|---|---|---|---|
| predict 3 parametric lights instead of Gardner et al. environment map | Ours · Laval Indoor HDR test | si-RMSE: 40% increase in median estimation performance | Improved |
| increase number of estimated lights from 2 to 3 (ablation) | Ours · Laval Indoor HDR test | si-RMSE | Improved |
| increase number of estimated lights from 3 to 5 (ablation) | Ours · Laval Indoor HDR test | si-RMSE | Hurt |
| increase number of estimated lights from 2 to 3 to 5 (ablation) | Ours · Laval Indoor HDR test | RMSE | Improved |
| add first training step before the direct loss (two-step training) (ablation) | Ours · Laval Indoor HDR test | si-RMSE: an order of magnitude lower error | Improved |
Closest papers by meaning
- Neural Illumination: Lighting Prediction for Indoor Environments (CVPR 2019 · similarity 0.92)
- Fast Spatially-Varying Indoor Lighting Estimation (CVPR 2019 · similarity 0.91)
- LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation (CVPR 2024 · similarity 0.88)
- LuxDiT: Lighting Estimation with Video Diffusion Transformer (NeurIPS 2025 · similarity 0.86)
- ROGR: Relightable 3D Objects using Generative Relighting (NeurIPS 2025 · similarity 0.86)
- LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting (CVPR 2025 · similarity 0.85)
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.
