mlsanityData to 14 Oct 2026

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

arXiv 2308.13164 ↗First posted 25 Aug 2023cs.CV eess.IVcited by 118

On the map: Diffusion models → Inverse problems and image restoration

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.

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.

Builds on

21 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution14 Feb

Other references · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  7. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  8. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 723
  9. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  10. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  11. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  12. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
8 more
  1. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  2. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 156
  3. 2018Joint Enhancement and Denoising Method via Sequential Decompositioncited by 32
  4. 2021Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Visioncited by 22
  5. 2023Bilevel Fast Scene Adaptation for Low-Light Image Enhancementcited by 22
  6. 2019Underexposed Image Correction via Hybrid Priors Navigated Deep Propagationcited by 8
  7. 2022Practical exposure correction via compensationcited by 5
  8. 2022Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancementcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 12; 2024: 35; 2025: 48; 2026: 23.

118 papers.

Sort:

By area:

  1. 2023Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restorationcited by 88
  2. 2024Diffusion Models in Low-Level Vision: A Surveycited by 74
  3. 2024LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Modelscited by 71
  4. 2023Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Modelcited by 69
  5. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 63
  6. 2024Zero-Reference Low-Light Enhancement via Physical Quadruple Priorscited by 58
  7. 2024Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Taskscited by 48
  8. 2024MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Spacecited by 48
  9. 2025UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Priorcited by 42
  10. 2024Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Drivingcited by 35
  11. 2024Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Networkcited by 26
  12. 2024Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancementcited by 25
38 more
  1. 2024You Only Need One Color Space: An Efficient Network for Low-light Image Enhancementcited by 24
  2. 2023Towards Real-World Blind Face Restoration with Generative Diffusion Priorcited by 22
  3. 2024LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancementcited by 22
  4. 2024Towards Real-world Event-guided Low-light Video Enhancement and Deblurringcited by 22
  5. 2025UniUIR: Considering Underwater Image Restoration as An All-in-One Learnercited by 22
  6. 2025UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restorationcited by 22
  7. 2023Boosting Object Detection with Zero-Shot Day-Night Domain Adaptationcited by 17
  8. 2024OmniCount: Multi-label Object Counting with Semantic-Geometric Priorscited by 16
  9. 2024AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancementcited by 16
  10. 2024Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observationcited by 16
  11. 2024A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolutioncited by 15
  12. 2025LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesiscited by 14
  13. 2024Efficient Diffusion as Low Light Enhancercited by 13
  14. 2025MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairscited by 13
  15. 2025Dereflection Any Image with Diffusion Priors and Diversified Datacited by 12
  16. 2025Low-Light Image Enhancement using Event-Based Illumination Estimationcited by 12
  17. 2025MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devicescited by 12
  18. 2024RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancementcited by 11
  19. 2025Learning to See in the Extremely Darkcited by 11
  20. 2025Reversible Unfolding Network for Concealed Visual Perception with Generative Refinementcited by 11
  21. 2024LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyondcited by 10
  22. 2023JoReS-Diff: Joint Retinex and Semantic Priors in Diffusion Model for Low-light Image Enhancementcited by 8
  23. 2023A Comprehensive Study of Object Tracking in Low-Light Environmentscited by 8
  24. 2025Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazingcited by 8
  25. 2023Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidancecited by 7
  26. 2023DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Modelcited by 6
  27. 2025Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devicescited by 6
  28. 2024DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancementcited by 5
  29. 2024Learning Efficient and Effective Trajectories for Differential Equation-based Image Restorationcited by 5
  30. 2024Taming Generative Diffusion Prior for Universal Blind Image Restorationcited by 4
  31. 2024Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priorscited by 4
  32. 2024Learning Adaptive Lighting via Channel-Aware Guidancecited by 4
  33. 2024Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE)cited by 4
  34. 2025ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancementcited by 4
  35. 2025FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restorationcited by 4
  36. 2023LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Modelscited by 3
  37. 2024Unveiling the Truth: Exploring Human Gaze Patterns in Fake Imagescited by 3
  38. 2024Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancementcited by 3

50 most cited of 118 All 118 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Retinex-Diffusion: On Controlling Illumination Conditions in Diffusion Models via Retinex Theory
  2. 2026DARD: Zero-Shot Degradation-Aware Retinex-Guided Diffusion for Low-Light Image Enhancement
  3. 2025IllumFlow: Illumination-Adaptive Low-Light Enhancement via Conditional Rectified Flow and Retinex Decomposition
  4. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Models
  5. 2026Single-Stage Signal Attenuation Diffusion Model for Low-Light Image Enhancement and Denoising
  6. 2024Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement
  7. 2023LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement
  8. 2024Personalized Generative Low-light Image Denoising and Enhancement