提出新损失函数，解决低光图像增强中的亮度不匹配问题。
GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement
- 从概率角度建模图像均值，设计新损失函数GT-mean
- 在多个方法和数据集上提升增强效果，性能稳定改善
- 简单易用，可无缝集成到现有模型中，适合低光增强研究者
低光图像增强（LLIE）旨在提升弱光条件下拍摄图像的视觉质量。在监督式LLIE研究中，增强图像与真实图像之间的整体亮度存在显著但常被忽视的不一致，本文称之为亮度不匹配。这种不匹配会误导模型训练，但当前研究对此问题关注不足。为此，本文提出一种简单而有效的损失函数——GT-mean损失，从概率视角直接建模图像的均值。该损失函数具有灵活性，可将现有监督式LLIE损失函数以极小计算开销扩展为GT-mean形式。大量实验表明，引入GT-mean损失后，多种方法在多个数据集上均实现一致的性能提升。
原文摘要 · Abstract (English)
Low-light image enhancement (LLIE) aims to improve the visual quality of images captured under poor lighting conditions. In supervised LLIE research, there exists a significant yet often overlooked inconsistency between the overall brightness of an enhanced image and its ground truth counterpart, referred to as brightness mismatch in this study. Brightness mismatch negatively impact supervised LLIE models by misleading model training. However, this issue is largely neglected in current research. In this context, we propose the GT-mean loss, a simple yet effective loss function directly modeling the mean values of images from a probabilistic perspective. The GT-mean loss is flexible, as it extends existing supervised LLIE loss functions into the GT-mean form with minimal additional computational costs. Extensive experiments demonstrate that the incorporation of the GT-mean loss results in consistent performance improvements across various methods and datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。