# Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model

arXiv: https://arxiv.org/abs/2308.13164 · HTML: https://mlsanity.com/paper/2308.13164/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 25 Aug 2023.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (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)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [The 2018 PIRM Challenge on Perceptual Image Super-resolution](https://mlsanity.com/paper/1809.07517/) (2018)
- [Joint Enhancement and Denoising Method via Sequential Decomposition](https://mlsanity.com/paper/1804.08468/) (2018)
- [Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision](https://mlsanity.com/paper/2112.04719/) (2021)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution](https://mlsanity.com/paper/2302.12831/) (2023)
- [Underexposed Image Correction via Hybrid Priors Navigated Deep Propagation](https://mlsanity.com/paper/1907.07408/) (2019)
- [Practical exposure correction via compensation](https://mlsanity.com/paper/2212.14245/) (2022)
- [Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement](https://mlsanity.com/paper/2207.00965/) (2022)

## Built on by (most cited first, 30 of 118)

- [Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration](https://mlsanity.com/paper/2311.16845/) (2023)
- [Diffusion Models in Low-Level Vision: A Survey](https://mlsanity.com/paper/2406.11138/) (2024)
- [LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models](https://mlsanity.com/paper/2407.08939/) (2024)
- [Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model](https://mlsanity.com/paper/2311.11638/) (2023)
- [HVI: A New Color Space for Low-light Image Enhancement](https://mlsanity.com/paper/2502.20272/) (2025)
- [Zero-Reference Low-Light Enhancement via Physical Quadruple Priors](https://mlsanity.com/paper/2403.12933/) (2024)
- [Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks](https://mlsanity.com/paper/2403.00644/) (2024)
- [MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space](https://mlsanity.com/paper/2405.16105/) (2024)
- [UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior](https://mlsanity.com/paper/2501.13134/) (2025)
- [Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving](https://mlsanity.com/paper/2404.04804/) (2024)
- [Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network](https://mlsanity.com/paper/2406.07966/) (2024)
- [Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2403.01497/) (2024)
- [You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement](https://mlsanity.com/paper/2402.05809/) (2024)
- [Towards Real-World Blind Face Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2312.15736/) (2023)
- [LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement](https://mlsanity.com/paper/2401.15204/) (2024)
- [Towards Real-world Event-guided Low-light Video Enhancement and Deblurring](https://mlsanity.com/paper/2408.14916/) (2024)
- [UniUIR: Considering Underwater Image Restoration as An All-in-One Learner](https://mlsanity.com/paper/2501.12981/) (2025)
- [UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration](https://mlsanity.com/paper/2505.06683/) (2025)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [OmniCount: Multi-label Object Counting with Semantic-Geometric Priors](https://mlsanity.com/paper/2403.05435/) (2024)
- [AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement](https://mlsanity.com/paper/2407.14900/) (2024)
- [Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation](https://mlsanity.com/paper/2411.16810/) (2024)
- [A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution](https://mlsanity.com/paper/2404.15620/) (2024)
- [LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesis](https://mlsanity.com/paper/2504.10331/) (2025)
- [Efficient Diffusion as Low Light Enhancer](https://mlsanity.com/paper/2410.12346/) (2024)
- [MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs](https://mlsanity.com/paper/2504.06897/) (2025)
- [Dereflection Any Image with Diffusion Priors and Diversified Data](https://mlsanity.com/paper/2503.17347/) (2025)
- [Low-Light Image Enhancement using Event-Based Illumination Estimation](https://mlsanity.com/paper/2504.09379/) (2025)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement](https://mlsanity.com/paper/2404.01889/) (2024)

## Abstract (arXiv)

In this paper, we rethink the low-light image enhancement task and propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex. We aim to integrate the advantages of the physical model and the generative network. Furthermore, we hope to supplement and even deduce the information missing in the low-light image through the generative network. Therefore, Diff-Retinex formulates the low-light image enhancement problem into Retinex decomposition and conditional image generation. In the Retinex decomposition, we integrate the superiority of attention in Transformer and meticulously design a Retinex Transformer decomposition network (TDN) to decompose the image into illumination and reflectance maps. Then, we design multi-path generative diffusion networks to reconstruct the normal-light Retinex probability distribution and solve the various degradations in these components respectively, including dark illumination, noise, color deviation, loss of scene contents, etc. Owing to generative diffusion model, Diff-Retinex puts the restoration of low-light subtle detail into practice. Extensive experiments conducted on real-world low-light datasets qualitatively and quantitatively demonstrate the effectiveness, superiority, and generalization of the proposed method.