重温图像融合技术在多光源白平衡校正中的应用

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

在多光源场景下的白平衡（WB）校正一直是计算机视觉领域的一个持续挑战。近期的方法探索了基于融合的策略，即通过神经网络线性混合输入图像的多个sRGB版本，每个版本都经过预定义的白平衡预设处理。然而，我们证明这些方法在常见的多光源场景下表现欠佳。此外，现有的融合方法依赖于缺乏专门多光源图像的sRGB白平衡数据集，这限制了训练和评估的效果。为解决这些问题，我们提出了两项关键贡献。首先，我们提出了一种高效的基于Transformer的模型，该模型能有效捕捉sRGB白平衡预设间的空间依赖关系，显著优于线性融合技术。其次，我们引入了一个大规模的多光源数据集，包含超过16,000张采用五种不同白平衡设置渲染的sRGB图像，以及经过白平衡校正的图像。在我们的新多光源图像融合数据集上，我们的方法相比现有技术实现了高达100%的性能提升。

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.