In this paper, we rethink the low-light image enhancement task and propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex. We aim to integrate the advantages of the physical model and the generative network. Furthermore, we hope to supplement and even deduce the information missing in the low-light image through the generative network. Therefore, Diff-Retinex formulates the low-light image enhancement problem into Retinex decomposition and conditional image generation. In the Retinex decomposition, we integrate the superiority of attention in Transformer and meticulously design a Retinex Transformer decomposition network (TDN) to decompose the image into illumination and reflectance maps. Then, we design multi-path generative diffusion networks to reconstruct the normal-light Retinex probability distribution and solve the various degradations in these components respectively, including dark illumination, noise, color deviation, loss of scene contents, etc. Owing to generative diffusion model, Diff-Retinex puts the restoration of low-light subtle detail into practice. Extensive experiments conducted on real-world low-light datasets qualitatively and quantitatively demonstrate the effectiveness, superiority, and generalization of the proposed method.

翻译：本文重新审视低光图像增强任务，并提出一种物理可解释的生成扩散模型用于低光图像增强，命名为Diff-Retinex。我们旨在融合物理模型与生成网络的优势，进而期望通过生成网络补充甚至推导低光图像中缺失的信息。为此，Diff-Retinex将低光图像增强问题分解为Retinex分解与条件图像生成两个子任务。在Retinex分解阶段，我们整合Transformer中注意力机制的优越性，精心设计了一种Retinex Transformer分解网络（TDN），将图像分解为光照图和反射率图。随后，我们构建多路径生成扩散网络，以重建正常光照条件下的Retinex概率分布，并分别解决这些分量中的各类退化问题，包括暗光照、噪声、色彩偏差、场景内容缺失等。得益于生成扩散模型，Diff-Retinex实现了低光图像细微细节的恢复。在真实低光数据集上进行的定性与定量实验充分证明了所提方法的有效性、优越性与泛化能力。