Low-light Image Enhancement with Retinex Decomposition in Latent Space

TL;DR

This paper introduces a Retinex-Guided Transformer model that improves low-light image enhancement by accurately decomposing reflectance and illumination in latent space, leading to better detail preservation and stable training.

Contribution

The paper presents a novel latent space decomposition strategy and a transformer-based component refiner for improved low-light image enhancement.

Findings

Achieves competitive performance on four benchmark datasets.

Provides more stable training process.

Enhances texture detail preservation.

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.