mlsanityData to 7 Oct 2026

Low-Light Image Enhancement with Normalizing Flow

arXiv 2109.05923 ↗First posted 13 Sep 2021eess.IV cs.CVcited by 184

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the mapping relationship between them is one-to-many. Previous works based on the pixel-wise reconstruction losses and deterministic processes fail to capture the complex conditional distribution of normally exposed images, which results in improper brightness, residual noise, and artifacts. In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution. In this way, the conditional distribution of the normally exposed images can be well modeled, and the enhancement process, i.e., the other inference direction of the invertible network, is equivalent to being constrained by a loss function that better describes the manifold structure of natural images during the training. The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.

Key facts. Cited by 184 papers in the map (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

30 of 43 references.

References · 30

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  6. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  7. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  8. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  9. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  10. 2018Learning to See in the Darkcited by 459
  11. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  12. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
18 more
  1. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  2. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  3. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  4. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  5. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  6. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  7. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  8. 2020Invertible Image Rescalingcited by 92
  9. 2021Invertible Denoising Network: A Light Solution for Real Noise Removalcited by 68
  10. 2019Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Datasetcited by 65
  11. 2018Conditional Density Estimation with Bayesian Normalising Flowscited by 54
  12. 2019C-Flow: Conditional Generative Flow Models for Images and 3D Point Cloudscited by 50
  13. 2017MSR-net:Low-light Image Enhancement Using Deep Convolutional Networkcited by 43
  14. 2017A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancementcited by 38
  15. 2018Joint Enhancement and Denoising Method via Sequential Decompositioncited by 32
  16. 2021DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flowscited by 30
  17. 2019Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancementcited by 29
  18. 2019Conditional Adversarial Generative Flow for Controllable Image Synthesiscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 19; 2023: 50; 2024: 40; 2025: 43; 2026: 31.

184 papers.

Sort:

By area:

  1. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  2. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  3. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 102
  4. 2023Global Structure-Aware Diffusion Process for Low-Light Image Enhancementcited by 92
  5. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 91
  6. 2023Low-Light Image Enhancement via Structure Modeling and Guidancecited by 78
  7. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  8. 2023Residual Denoising Diffusion Modelscited by 68
  9. 2023Pyramid Diffusion Models For Low-light Image Enhancementcited by 67
  10. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 62
  11. 2024Zero-Reference Low-Light Enhancement via Physical Quadruple Priorscited by 58
  12. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
38 more
  1. 2023Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancementcited by 57
  2. 2023Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Triggercited by 40
  3. 2023Lighting up NeRF via Unsupervised Decomposition and Enhancementcited by 40
  4. 2023Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolutioncited by 39
  5. 2023ShadowFormer: Global Context Helps Image Shadow Removalcited by 35
  6. 2022Low-Light Video Enhancement with Synthetic Event Guidancecited by 33
  7. 2024GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrievalcited by 33
  8. 2023CLE Diffusion: Controllable Light Enhancement Diffusion Modelcited by 30
  9. 2023ExposureDiffusion: Learning to Expose for Low-light Image Enhancementcited by 29
  10. 2023Human Pose Estimation in Extremely Low-Light Conditionscited by 27
  11. 2025Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restorationcited by 27
  12. 2024You Only Need One Color Space: An Efficient Network for Low-light Image Enhancementcited by 24
  13. 2024Perception-Oriented Video Frame Interpolation via Asymmetric Blendingcited by 23
  14. 2022Memories are One-to-Many Mapping Alleviators in Talking Face Generationcited by 22
  15. 2024Reversible Decoupling Network for Single Image Reflection Removalcited by 22
  16. 2022Half Wavelet Attention on M-Net+ for Low-Light Image Enhancementcited by 20
  17. 2023Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognitioncited by 20
  18. 2023Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noisecited by 19
  19. 2022Learn from Unpaired Data for Image Restoration: A Variational Bayes Approachcited by 18
  20. 2023Raw Image Reconstruction with Learned Compact Metadatacited by 18
  21. 2022Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyondcited by 17
  22. 2024AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancementcited by 16
  23. 2024LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenescited by 16
  24. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  25. 2023LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusioncited by 15
  26. 2023LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancementcited by 15
  27. 2024Multi-Object Tracking in the Darkcited by 14
  28. 2024Color Shift Estimation-and-Correction for Image Enhancementcited by 14
  29. 2024LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Networkcited by 14
  30. 2025Brightness Perceiving for Recursive Low-Light Image Enhancementcited by 14
  31. 2024Efficient Diffusion as Low Light Enhancercited by 13
  32. 2022Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Datacited by 12
  33. 2023Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillancecited by 12
  34. 2023VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebookcited by 12
  35. 2024LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusioncited by 12
  36. 2022Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustmentcited by 10
  37. 2023Similarity Min-Max: Zero-Shot Day-Night Domain Adaptationcited by 10
  38. 2025Reversing Flow for Image Restorationcited by 10

50 most cited of 184 All 184 (JSON)