Research map / Image generation / Image restoration
Deep White-Balance Editing
Mahmoud Afifi, Michael S. Brown
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 |
|---|---|---|---|
| Use the multi-decoder network instead of KNN-WB for AWB correction | AWB correction · Rendered WB Set 1-Test | MSE (mean): 77.79 -> 82.55 | Hurt |
| Use the multi-decoder network instead of KNN-WB for AWB correction | AWB correction · Rendered WB Set 2 | MSE (mean): 171.09 -> 124.97 | Improved |
| Use the multi-decoder network instead of KNN-WB for AWB correction | AWB correction · Rendered Cube+ | MSE (mean): 194.98 -> 80.46 | Improved |
| Use the multi-decoder network instead of KNN-WB emulator for WB manipulation | WB manipulation · Rendered Cube+ | MSE (mean): 317.25 -> 199.38 | Improved |
| Use the multi-decoder network instead of KNN-WB emulator for WB manipulation | WB manipulation · Rendered MIT-Adobe FiveK | MSE (mean): 249.95 -> 135.71 | Improved |
| Replace the shared encoder and multiple decoders with separate U-Nets (ablation) | Deep White-Balance Editing · Rendered WB Set 2 (AWB) | MSE: 124.47 -> 187.25 | Hurt |
| Replace the shared encoder and multiple decoders with separate U-Nets (ablation) | Deep White-Balance Editing · Rendered Cube+ (WB editing) | MSE: 206.81 -> 234.77 | Hurt |
| Use L2 loss instead of L1 loss (ablation) | Deep White-Balance Editing · WB editing | reconstruction quality | No clear effect |
| Estimate the polynomial mapping matrix directly instead of fitting it to generated image output (ablation) | Deep White-Balance Editing · WB editing | mapping robustness | Hurt |
Closest papers by meaning
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.87)
- HVDualformer: Histogram-Vision Dual Transformer for White Balance (AAAI 2025 · similarity 0.86)
- Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing (CVPR 2024 · similarity 0.86)
- White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation (CVPR 2026 · similarity 0.86)
- ABC-Former: Auxiliary Bimodal Cross-domain Transformer with Interactive Channel Attention for White Balance (CVPR 2025 · similarity 0.85)
- Logarithmic Lenses: Exploring Log RGB Data for Image Classification (CVPR 2024 · 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.
