Research map / Image generation / Image restoration
Two Illuminant Estimation and User Correction Preference
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 |
|---|---|---|---|
| Estimate illuminants on large 4 × 6 sub-images using multiple regression trees and combine reliable estimates | Two-illuminant estimation · Gehler-Shi single-illuminant images | F-measure: 0.9578 | Helped |
| Estimate illuminants on large 4 × 6 sub-images using multiple regression trees and combine reliable estimates | Two-illuminant estimation · Gehler-Shi double-illuminant images | F-measure: 0.7000 | Helped |
| Use an 8 × 12 grid instead of a 4 × 6 grid (ablation) | Proposed two-illuminant estimator · Gehler-Shi single-illuminant images | F-measure: 0.9578 -> 0.9450 | Hurt |
| Use an 8 × 12 grid instead of a 4 × 6 grid (ablation) | Proposed two-illuminant estimator · Gehler-Shi double-illuminant images | F-measure: 0.7000 -> 0.6494 | Hurt |
| Use an 8 × 12 grid instead of a 4 × 6 grid (ablation) | Proposed two-illuminant estimator · Gehler-Shi double-illuminant images | angular error: 1.87 -> 2.32 | Hurt |
| Replace multiple regression trees with locally applied Grey-world | Two-illuminant estimator · Gehler-Shi double-illuminant images | F-measure: 0.7000 -> 0.3125 | Hurt |
| Replace multiple regression trees with locally applied Corrected-Moment | Two-illuminant estimator · Gehler-Shi double-illuminant images | F-measure: 0.7000 -> 0.4649 | Hurt |
| Use adapted local-window Gijsenij et al. estimation | Two-illuminant estimator · Gehler-Shi double-illuminant images | F-measure: 0.7000 -> 0.2762 | Hurt |
| Correct with the outdoor illuminant rather than the indoor illuminant | Global white-balance correction for distinct indoor/outdoor illuminants · User Study 1, 33 images | user preference: almost 80% | Helped |
| Use a correction weighted toward the outdoor illuminant (L4) | Global white-balance correction for distinct illuminants · User Study 2, Cat. I | user preference | Helped |
| Use a correction weighted toward the outdoor illuminant | Global white-balance correction for similar illuminants · User Study 2, Cat. II | user preference | No clear effect |
Closest papers by meaning
- Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing (CVPR 2024 · similarity 0.89)
- Do Image Editing Models Understand Lighting? (NeurIPS 2026 · similarity 0.86)
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · similarity 0.84)
- White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation (CVPR 2026 · similarity 0.84)
- Illumination Spectrum Estimation for Multispectral Images via Surface Reflectance Modeling and Spatial-Spectral Feature Generation (CVPR 2025 · similarity 0.84)
- Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment (CVPR 2025 · similarity 0.84)
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.