Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models. In this study, we propose ReCo-Diff, a novel approach that incorporates Retinex-based prior as an additional pre-processing condition to regulate the generating capabilities of the diffusion model. ReCo-Diff first leverages a pre-trained decomposition network to produce initial reflectance and illumination maps of the low-light image. Then, an adjustment network is introduced to suppress the noise in the reflectance map and brighten the illumination map, thus forming the learned Retinex-based condition. The condition is integrated into a refinement network, implementing Retinex-based conditional modules that offer sufficient guidance at both feature- and image-levels. By treating Retinex theory as a condition, ReCo-Diff presents a unique perspective for establishing an LLIE-specific diffusion model. Extensive experiments validate the rationality and superiority of our ReCo-Diff approach. The code will be made publicly available.

翻译：低光图像增强（LLIE）通过采用条件扩散模型已取得令人瞩目的性能。本研究提出ReCo-Diff，一种将Retinex先验作为额外预处理条件以调控扩散模型生成能力的新方法。ReCo-Diff首先利用预训练分解网络生成低光图像的初始反射分量与光照分量，随后引入调整网络抑制反射分量噪声并增强光照分量，从而构建学习型Retinex条件。该条件被集成至细化网络中，通过特征级与图像级双重引导实现Retinex条件模块。将Retinex理论作为条件，ReCo-Diff为建立面向LLIE的扩散模型提供了独特视角。大量实验验证了ReCo-Diff方法的合理性与优越性，相关代码将公开发布。