English

Revisiting Image Fusion for Multi-Illuminant White-Balance Correction

Computer Vision and Pattern Recognition 2025-03-20 v1

Abstract

White balance (WB) correction in scenes with multiple illuminants remains a persistent challenge in computer vision. Recent methods explored fusion-based approaches, where a neural network linearly blends multiple sRGB versions of an input image, each processed with predefined WB presets. However, we demonstrate that these methods are suboptimal for common multi-illuminant scenarios. Additionally, existing fusion-based methods rely on sRGB WB datasets lacking dedicated multi-illuminant images, limiting both training and evaluation. To address these challenges, we introduce two key contributions. First, we propose an efficient transformer-based model that effectively captures spatial dependencies across sRGB WB presets, substantially improving upon linear fusion techniques. Second, we introduce a large-scale multi-illuminant dataset comprising over 16,000 sRGB images rendered with five different WB settings, along with WB-corrected images. Our method achieves up to 100\% improvement over existing techniques on our new multi-illuminant image fusion dataset.

Keywords

Cite

@article{arxiv.2503.14774,
  title  = {Revisiting Image Fusion for Multi-Illuminant White-Balance Correction},
  author = {David Serrano-Lozano and Aditya Arora and Luis Herranz and Konstantinos G. Derpanis and Michael S. Brown and Javier Vazquez-Corral},
  journal= {arXiv preprint arXiv:2503.14774},
  year   = {2025}
}

Comments

10 pages