Research map / 3D vision / Depth and stereo
All-Weather Deep Outdoor Lighting Estimation
Jinsong Zhang, Kalyan Sunkavalli, Yannick Hold-Geoffroy, Sunil Hadap, Jonathan Eisenman, Jean-Francois Lalonde
Check 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 the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, clear (shadow softness 1) | RMSE: 1.07 -> 0.92 | Improved |
| Add the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, mixed (shadow softness 2) | RMSE: 0.55 -> 0.41 | Improved |
| Add the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, cloudy (shadow softness 3) | RMSE: 0.59 -> 0.36 | Improved |
| Add the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, all | RMSE: 0.82 -> 0.73 | Improved |
| Add the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, clear (shadow softness 1) | si-RMSE: 0.19 -> 0.15 | Improved |
| Add the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, mixed (shadow softness 2) | si-RMSE: 0.13 -> 0.11 | Improved |
| Add the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, cloudy (shadow softness 3) | si-RMSE: 0.08 -> 0.09 | Hurt |
| Add the additional losses to the parametric loss (ablation) | PanoNet · HDR outdoor panoramas, all | si-RMSE: 0.16 -> 0.13 | Improved |
| Use learned panorama labeling and LM lighting parameters rather than direct HW model fitting | PanoNet · HDR outdoor panoramas across clear to overcast conditions | render error | Improved |
| Estimate lighting from a crop with CropNet rather than the prior method | CropNet · HDR outdoor panorama crops across weather conditions | render error | Improved |
Closest papers by meaning
- Deep Outdoor Illumination Estimation (CVPR 2017 · similarity 0.93)
- Deep Sky Modeling for Single Image Outdoor Lighting Estimation (CVPR 2019 · similarity 0.92)
- Spatially-Varying Outdoor Lighting Estimation From Intrinsics (CVPR 2021 · similarity 0.90)
- Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks (IJCV 2022 · similarity 0.89)
- Hierarchical Disentangled Representation Learning for Outdoor Illumination Estimation and Editing (ICCV 2021 · similarity 0.89)
- LuxDiT: Lighting Estimation with Video Diffusion Transformer (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.
