Low-light Image Enhancement with Retinex Decomposition in Latent Space

Abstract

Retinex theory provides a principled foundation for low-light image enhancement, inspiring numerous learning-based methods that integrate its principles. However, existing methods exhibits limitations in accurately decomposing reflectance and illumination components. To address this, we propose a Retinex-Guided Transformer~(RGT) model, which is a two-stage model consisting of decomposition and enhancement phases. First, we propose a latent space decomposition strategy to separate reflectance and illumination components. By incorporating the log transformation and 1-pixel offset, we convert the intrinsically multiplicative relationship into an additive formulation, enhancing decomposition stability and precision. Subsequently, we construct a U-shaped component refiner incorporating the proposed guidance fusion transformer block. The component refiner refines reflectance component to preserve texture details and optimize illumination distribution, effectively transforming low-light inputs to normal-light counterparts. Experimental evaluations across four benchmark datasets validate that our method achieves competitive performance in low-light enhancement and a more stable training process.

Figures (12)

• Figure 1: Comparison between the typical Retinex decomposition strategy and our method in deep learning frameworks.
• Figure 2: The overview of the RGT model. (a) Decomposition takes a paired low-light/normal-light image as input during training to decompose the image into $R$ and $L$ components. (b) RGT extracts $R$ and $L$ using the pre-trained decomposition network (frozen parameters) and enhances $R$ and $L$ separately via the Enhancer network (non-shared parameters). Then, reconstructing the final enhanced result by combining processed $R$ and $L$.
• Figure 3: The architecture of the GFTB.
• Figure 4: Schematic illustration of illumination-reflectance component swapping between two content-identical images under different lighting conditions. Each input image is decomposed into reflectance ($R$) and illumination ($L$) components within the shallow spatial space. By exclusively exchanging the $L$ components between paired images, we can synthesize four novel recomposed results. Ideally, swapping only the $L$ components is sufficient to alter the brightness of the images.
• Figure 5: Visual comparisons of the decomposed results by different methods on LOLv2_real. The images within the green boxes should be same and the images within the red boxes should be same.