mlsanityData to 7 Oct 2026

EnlightenGAN: Deep Light Enhancement without Paired Supervision

arXiv 1906.06972 ↗First posted 17 Jun 2019cs.CV eess.IVcited by 466

Not on the map. Why?

Cited by 47 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a self-regularized perceptual loss fusion, and attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. The code is available at urlhttps://github.com/yueruchen/EnlightenGAN

Key facts. Cited by 466 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 58; 2022: 61; 2023: 107; 2024: 83; 2025: 90; 2026: 67.

466 papers.

Sort:

By area:

  1. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  2. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  3. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 198
  4. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  5. 2021Low-Light Image Enhancement with Normalizing Flowcited by 184
  6. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  7. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  8. 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
  9. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  10. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 126
  11. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
  12. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
38 more
  1. 2023Iterative Prompt Learning for Unsupervised Backlit Image Enhancementcited by 107
  2. 2021R2RNet: Low-light Image Enhancement via Real-low to Real-normal Networkcited by 106
  3. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 102
  4. 2021RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Contentcited by 100
  5. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 95
  6. 2023Implicit Neural Representation for Cooperative Low-light Image Enhancementcited by 92
  7. 2023Global Structure-Aware Diffusion Process for Low-Light Image Enhancementcited by 92
  8. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  9. 2023Low-Light Image Enhancement via Structure Modeling and Guidancecited by 78
  10. 2022Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppressioncited by 73
  11. 2024LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Modelscited by 70
  12. 2023Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Modelcited by 69
  13. 2023Pyramid Diffusion Models For Low-light Image Enhancementcited by 67
  14. 2021Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tablescited by 65
  15. 2021Low-light Image Enhancement via Breaking Down the Darknesscited by 65
  16. 2023FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Informationcited by 64
  17. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 62
  18. 2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
  19. 2021Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancementcited by 60
  20. 2022Multitask AET with Orthogonal Tangent Regularity for Dark Object Detectioncited by 59
  21. 2024Zero-Reference Low-Light Enhancement via Physical Quadruple Priorscited by 58
  22. 2021Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkcited by 57
  23. 2023Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancementcited by 57
  24. 2024MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Spacecited by 48
  25. 2024DarkIR: Robust Low-Light Image Restorationcited by 48
  26. 2023Instance Segmentation in the Darkcited by 45
  27. 2023Lighting up NeRF via Unsupervised Decomposition and Enhancementcited by 40
  28. 2022Multi-Bracket High Dynamic Range Imaging with Event Camerascited by 37
  29. 2023HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidancecited by 36
  30. 2023Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumptioncited by 35
  31. 2024Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Drivingcited by 35
  32. 2023Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Networkcited by 33
  33. 2024GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrievalcited by 33
  34. 2021StarEnhancer: Learning Real-Time and Style-Aware Image Enhancementcited by 32
  35. 2021Semantically Contrastive Learning for Low-light Image Enhancementcited by 31
  36. 2023CLE Diffusion: Controllable Light Enhancement Diffusion Modelcited by 30
  37. 2022Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Trainingcited by 29
  38. 2021HLA-Face: Joint High-Low Adaptation for Low Light Face Detectioncited by 28

50 most cited of 466 All 466 (JSON)