mlsanityData to 7 Oct 2026

Deep Retinex Decomposition for Low-Light Enhancement

arXiv 1808.04560 ↗First posted 14 Aug 2018cs.CVcited by 720

Not on the map. Why?

Cited by 85 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Retinex model is an effective tool for low-light image enhancement. It assumes that observed images can be decomposed into the reflectance and illumination. Most existing Retinex-based methods have carefully designed hand-crafted constraints and parameters for this highly ill-posed decomposition, which may be limited by model capacity when applied in various scenes. In this paper, we collect a LOw-Light dataset (LOL) containing low/normal-light image pairs and propose a deep Retinex-Net learned on this dataset, including a Decom-Net for decomposition and an Enhance-Net for illumination adjustment. In the training process for Decom-Net, there is no ground truth of decomposed reflectance and illumination. The network is learned with only key constraints including the consistent reflectance shared by paired low/normal-light images, and the smoothness of illumination. Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance. The Retinex-Net is end-to-end trainable, so that the learned decomposition is by nature good for lightness adjustment. Extensive experiments demonstrate that our method not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.

Key facts. Cited by 720 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 53; 2022: 69; 2023: 132; 2024: 154; 2025: 167; 2026: 145.

720 papers.

Sort:

By area:

  1. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  2. 2024OmniGen: Unified Image Generationcited by 388
  3. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
  4. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  5. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  6. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212
  7. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 198
  8. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  9. 2021Low-Light Image Enhancement with Normalizing Flowcited by 184
  10. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  11. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  12. 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
38 more
  1. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  2. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 126
  3. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
  4. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
  5. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  6. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
  7. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  8. 2023Iterative Prompt Learning for Unsupervised Backlit Image Enhancementcited by 107
  9. 2021R2RNet: Low-light Image Enhancement via Real-low to Real-normal Networkcited by 106
  10. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 102
  11. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  12. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 95
  13. 2023Implicit Neural Representation for Cooperative Low-light Image Enhancementcited by 92
  14. 2023Global Structure-Aware Diffusion Process for Low-Light Image Enhancementcited by 92
  15. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 91
  16. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  17. 2022You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correctioncited by 81
  18. 2023ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restorationcited by 77
  19. 2022Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppressioncited by 73
  20. 2024Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Modelcited by 73
  21. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  22. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restorationcited by 72
  23. 2022AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancementcited by 70
  24. 2024LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Modelscited by 70
  25. 2023Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Modelcited by 69
  26. 2023Residual Denoising Diffusion Modelscited by 68
  27. 2023Pyramid Diffusion Models For Low-light Image Enhancementcited by 67
  28. 2021Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tablescited by 65
  29. 2021Low-light Image Enhancement via Breaking Down the Darknesscited by 65
  30. 2023FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Informationcited by 64
  31. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 62
  32. 2024I2EBench: A Comprehensive Benchmark for Instruction-based Image Editingcited by 61
  33. 2021Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancementcited by 60
  34. 2024Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restorationcited by 60
  35. 2022Multitask AET with Orthogonal Tangent Regularity for Dark Object Detectioncited by 59
  36. 2024Retinexmamba: Retinex-based Mamba for Low-light Image Enhancementcited by 59
  37. 2024Zero-Reference Low-Light Enhancement via Physical Quadruple Priorscited by 58
  38. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58

50 most cited of 720 All 720 (JSON)