Revisiting Image Fusion for Multi-Illuminant White-Balance Correction
This addresses a persistent challenge in computer vision for applications like photography and image processing, but it is incremental as it builds on existing fusion-based approaches.
The paper tackles the problem of white balance correction in scenes with multiple illuminants by proposing a transformer-based model and a new dataset, achieving up to 100% improvement over existing methods on their multi-illuminant dataset.
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.