# Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment

arXiv: https://arxiv.org/abs/2202.05972 · HTML: https://mlsanity.com/paper/2202.05972/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 86 references that are in the map.
- First posted on arXiv 12 Feb 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [A Model-driven Deep Neural Network for Single Image Rain Removal](https://mlsanity.com/paper/2005.01333/) (2020)
- [Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2110.00984/) (2021)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement](https://mlsanity.com/paper/1911.11323/) (2019)
- [Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution](https://mlsanity.com/paper/1611.06495/) (2016)
- [Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement](https://mlsanity.com/paper/2112.05147/) (2021)
- [LIME: A Method for Low-light IMage Enhancement](https://mlsanity.com/paper/1605.05034/) (2016)
- [Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs](https://mlsanity.com/paper/2006.00439/) (2020)

## Built on by (most cited first, 10 of 10)

- [Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction](https://mlsanity.com/paper/2205.07471/) (2022)
- [LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Network](https://mlsanity.com/paper/2406.01028/) (2024)
- [Real-Time Multi-Scene Visibility Enhancement for Promoting Navigational Safety of Vessels Under Complex Weather Conditions](https://mlsanity.com/paper/2409.01500/) (2024)
- [RetinexDual: Retinex-based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration](https://mlsanity.com/paper/2508.04797/) (2025)
- [Simplifying Low-Light Image Enhancement Networks with Relative Loss Functions](https://mlsanity.com/paper/2304.02978/) (2023)
- [Low-light Stereo Image Enhancement and De-noising in the Low-frequency Information Enhanced Image Space](https://mlsanity.com/paper/2401.07753/) (2024)
- [Nonlocal Retinex-Based Variational Model and its Deep Unfolding Twin for Low-Light Image Enhancement](https://mlsanity.com/paper/2504.07810/) (2025)
- [Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization](https://mlsanity.com/paper/2403.01142/) (2024)
- [Poisson Informed Retinex Network for Extreme Low-Light Image Enhancement](https://mlsanity.com/paper/2506.04470/) (2025)
- [HistRetinex: Optimizing Retinex model in Histogram Domain for Efficient Low-Light Image Enhancement](https://mlsanity.com/paper/2510.21100/) (2025)

## Abstract (arXiv)

Motivated by their recent advances, deep learning techniques have been widely applied to low-light image enhancement (LIE) problem. Among which, Retinex theory based ones, mostly following a decomposition-adjustment pipeline, have taken an important place due to its physical interpretation and promising performance. However, current investigations on Retinex based deep learning are still not sufficient, ignoring many useful experiences from traditional methods. Besides, the adjustment step is either performed with simple image processing techniques, or by complicated networks, both of which are unsatisfactory in practice. To address these issues, we propose a new deep learning framework for the LIE problem. The proposed framework contains a decomposition network inspired by algorithm unrolling, and adjustment networks considering both global brightness and local brightness sensitivity. By virtue of algorithm unrolling, both implicit priors learned from data and explicit priors borrowed from traditional methods can be embedded in the network, facilitate to better decomposition. Meanwhile, the consideration of global and local brightness can guide designing simple yet effective network modules for adjustment. Besides, to avoid manually parameter tuning, we also propose a self-supervised fine-tuning strategy, which can always guarantee a promising performance. Experiments on a series of typical LIE datasets demonstrated the effectiveness of the proposed method, both quantitatively and visually, as compared with existing methods.