Research map / Image generation / Image restoration
SWBNet: A Stable White Balance Network for sRGB Images
Chunxiao Li, Xuejing Kang, Zhifeng Zhang, Anlong Ming
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 |
|---|---|---|---|
| Use SWBNet instead of KNN-WB | sRGB white balancing · Rendered Cube | ∆E2000 mean across color temperatures: 5.88 -> 4.88 | Improved |
| Use SWBNet instead of MixedWB | sRGB white balancing · Mixedscene | ∆E2000 mean across color temperatures: 10.25 -> 9.19 | Improved |
| Use SWBNet instead of MixedWB | sRGB white balancing · Mixedscene | ∆E2000 mean: 10.61 -> 9.19 | Improved |
| Use SWBNet instead of DWB | sRGB white balancing · Rendered Cube | ∆E2000 mean: 4.59 -> 4.28 | Improved |
| Replace the U-Net encoder with the CTIF extractor (ablation) | SWBNet · Rendered Cube and Mixedscene | ∆E2000 variation across color temperatures | Improved |
| Add CT-contrastive loss (ablation) | SWBNet · Rendered Cube and Mixedscene | ∆E2000 variation across color temperatures | Improved |
| Combine the CTIF extractor and CT-contrastive loss (ablation) | SWBNet · Rendered Cube and Mixedscene | ∆E2000 variation across color temperatures | Improved |
| Add the CTS-oriented transformer (ablation) | SWBNet · Rendered Cube and Mixedscene | ∆E2000 mean | Improved |
Later papers that compared with this method
2 later accepted papers report SWBNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Revisiting Image Fusion for Multi-Illuminant White-Balance Correction (ICCV 2025 · better on 5 of 5 shared results)
- HVDualformer: Histogram-Vision Dual Transformer for White Balance (AAAI 2025 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ABC-Former: Auxiliary Bimodal Cross-domain Transformer with Interactive Channel Attention for White Balance (CVPR 2025 · similarity 0.88)
- HVDualformer: Histogram-Vision Dual Transformer for White Balance (AAAI 2025 · similarity 0.88)
- Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing (CVPR 2024 · similarity 0.84)
- ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation (NeurIPS 2025 · similarity 0.84)
- White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation (CVPR 2026 · similarity 0.84)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.83)
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.
