ARetinex-Net: Low-light image enhancement with adaptive retinex model and global illumination representation.

IA2former: Illumination-Aware Attention-based Transformer for Low-light Image Enhancement

Low-light image enhancement has made significant progress through both traditional Retinex methods and deep learning techniques. Traditional Retinex-based methods decompose images into illumination and reflectance components to mimic human perception of brightness and color. However, these methods often struggle with noise suppression and detail preservation, particularly under severe low-light conditions. Recent Transformer-based methods, such as RetinexFormer and Restormer, have improved restoration performance by modeling long-range dependencies, but they still insufficiently explore the interaction between illumination variations and spatial--semantic features. To address these limitations, we propose Illumination-Aware Attention-based Transformer (IA2former), a novel low-light image enhancement model that explicitly models illumination-aware feature interactions. By integrating an Illumination-Aware Attention mechanism and an Illumination-Aware Loss function, IA2former effectively captures long-range dependencies, improves detail restoration, and preserves spatial structures under challenging illumination conditions. Experimental evaluations on the LOL-v1 and LOL-v2 datasets demonstrate that IA2former achieves a favorable overall balance across PSNR, SSIM, and LPIPS, obtaining the best performance on multiple metrics and remaining competitive on others. These results validate the effectiveness and robustness of the proposed illumination-aware modeling strategy for low-light image enhancement.

WREN: Low Light Image Enhancement Using Retinex Theory-Based Double U-Net-Like Structures

This paper proposes a neural network for low light image enhancement (LLIE) based on retinex theory to make LLIE robust for various dynamic range scenes. The retinex theory is an image formulation model inspired by a human color perception hypothesis, where a low light image is decomposed into intrinsic color context (i.e., reflectance map) and scene-dependent illumination (i.e., illumination map). Due to non-uniqueness of its decomposition, existing retinex-based LLIE methods often fail to achieve stable decomposition, which lead to over-enhancement. Typically, they are sensitive to the dynamic ranges that vary in different lighting conditions. To tackle this issue, we propose WREN: An LLIE neural network with double U-Net-like structures. WREN consists of two U-Net-like sub-networks. The first network has one encoder and two decoders that decompose an input image into the reflectance and illumination maps. The second network with a customized Transformer block between an encoder and a decoder only enhances the illumination map obtained from the first network: This completely follows the assumption of the retinex theory. Finally, the enhanced illumination map is recombined with the reflectance map. The network is trained end-to-end with a scale-invariant loss function, which gives robustness against the illumination scaling. Numerical results show that our method achieves the state-of-the-art performance across multiple datasets. Our code is available online.

MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model

Images captured by consumer electronic devices, such as mobile phones and digital cameras, often suffer from low-light degradation due to sensor limitations and imaging pipelines, which degrades visual quality and affects downstream vision tasks. Existing methods based on Convolutional Neural Networks (CNNs) and Transformers have dominated current low-light image enhancement (LIE) due to their excellent ability to model hierarchical features. However, CNNs operate in local receptive fields that cannot model long-range dependencies, while Transformers overcome this problem but incur substantial computational costs. To address these challenges, we propose MambaLIE, a Scene Light Intensity-Boosted Low-Light Image Enhancement method based on a State Space Model (SSM). We first introduce scene light intensity to improve the structural distribution of illumination, which is then gated with the low-light input to guide enhancement. To better model the illumination while maintaining computational efficiency, we propose the Locally Enhanced State Space Model (LESSM) for efficient light enhancement. Our LESSM contains two branches: an SSM branch and a Local Enhanced branch, where the former is used to model the long-range dependencies with linear time complexity, while the latter is used to enhance local feature representations. Extensive experiments demonstrate that MambaLIE outperforms state-of-the-art CNN-based and Transformer-based LIE methods on four widely used synthetic benchmarks and five publicly available real-world benchmarks in terms of accuracy, speed, and model size, making it suitable for practical deployment on resource-constrained devices.

Modified Diff-Retinex Model for Robust Low-Light Image Enhancement

Improving images captured under low light is a common topic in computer vision. Applications range from surveillance, self-driving cars, and photography. However, classical Retinex-based algorithms suffer from over-enhancement, noise amplification, and color distortion. This is because they suppose that the resultant image can be separated into two components: illumination and reflectance. To overcome these issues, we propose a Modified Diff-Retinex Model, which combines the Retinex theory with a diffusion-based regularization term to achieve strong and visually pleasant image enhancement. We also use an adaptive edge-aware diffusion to estimate illumination, preserving structural details while eliminating noise. Unlike conventional Retinex, which assumes fixed priors or logarithmic transformations of the image, our model adapts to local changes in lighting and contrast in real time. We restore the original colors and brightness of the image via a post-enhancement refinement stage that reduces artifacts and improves visual quality. Experiments on publicly available low-light image datasets show that our model outperforms the state-of-the-art models and works better in terms of visual quality and quantitative metrics such as contrast, color, and noise reduction. The proposed method achieves an average PSNR of 16.2890 dB, SSIM of 0.6344, and LPIPS of 0.2628, demonstrating superior performance compared to existing low-light enhancement methods.

LCCNet: luminance–chroma collaborative cross-attention network for low-light image enhancement

UBLLIE: Unified Backlight and Low-Light Image Enhancement

Backlit and low-light images often suffer from severe exposure imbalance or global underexposure, presenting significant challenges for both visual perception and downstream computer vision tasks. In this paper, we propose a unified, unsupervised enhancement framework that addresses both types of degradation without relying on paired ground-truth data. Our approach builds on CLIP-guided prompt learning to semantically supervise enhancement using learned positive and negative textual prompts. To improve the quality of our improvements over prior work, we design a symmetric residual U-Net backbone augmented with an Atrous Spatial Pyramid Pooling module. This architecture captures multi-scale contextual information, enabling adaptive correction under spatially heterogeneous illumination. During training, the enhancement network is guided by CLIP-based semantic similarity losses and refined via an iterative prompt optimization mechanism. Extensive experiments on both paired and unpaired datasets, including BAID, Backlit300, LOL, and VE-LOL-L, demonstrate that our framework consistently outperforms state-of-the-art supervised and unsupervised methods in terms of fidelity, perceptual quality, and generalization. Furthermore, our work emphasizes the need for stronger benchmarking protocols for backlit enhancement, a relatively underexplored area. The proposed framework provides a robust, scalable solution for real-world illumination enhancement across diverse lighting conditions.