Exploring Multi-Feature Relationship in Retinex Decomposition for Low-Light Image Enhancement

Despite the recent advancements in deep learning techniques, existing unsupervised low-light image enhancement methods fail to improve global brightness and restore colour due to the lack of high-quality training targets. Moreover, real-world low-light images inevitably contain noise, which significantly reduces image visibility and quality, further complicating the enhancement process. However, current unsupervised approaches tend to oversimplify or ignore the noise in low-light images. To address these issues, we first revise the traditional Retinex decomposition to better integrate with unsupervised deep learning frameworks. Then, we design a Local and Global Illumination-Guided Network for removing corruption from the reflectance component, which improves enhancement quality by not only investigating multi-feature similarity and attention mechanism based on the Retinex theory but also leveraging local details and long-range dependencies. Furthermore, by analysing the attributes of corruption within the reflectance component, we introduce a novel reflectance enhancement loss to effectively remove noise without using ground truth.