重探圖像融合技術於多光源白平衡校正之應用

Revisiting Image Fusion for Multi-Illuminant White-Balance Correction

March 18, 2025

作者: David Serrano-Lozano, Aditya Arora, Luis Herranz, Konstantinos G. Derpanis, Michael S. Brown, Javier Vazquez-Corral

cs.AI

摘要

在多光源場景下的白平衡（WB）校正，一直是計算機視覺領域中一個持續存在的挑戰。近期的方法探索了基於融合的技術，其中神經網絡線性混合了輸入圖像的多個sRGB版本，每個版本都使用預定義的白平衡預設進行處理。然而，我們證明這些方法在常見的多光源場景下並非最優。此外，現有的基於融合的方法依賴於缺乏專用多光源圖像的sRGB白平衡數據集，這限制了訓練和評估的效果。為應對這些挑戰，我們提出了兩項關鍵貢獻。首先，我們提出了一種高效的基於Transformer的模型，該模型能有效捕捉跨sRGB白平衡預設的空間依賴性，顯著改進了線性融合技術。其次，我們引入了一個大規模的多光源數據集，包含超過16,000張使用五種不同白平衡設置渲染的sRGB圖像，以及經過白平衡校正的圖像。在我們新的多光源圖像融合數據集上，我們的方法相比現有技術實現了高達100%的提升。

English

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.