mlsanityData to 7 Oct 2026

Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond

arXiv 2212.10772 ↗First posted 21 Dec 2022cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

This paper presents a comprehensive survey of low-light image and video enhancement, addressing two primary challenges in the field. The first challenge is the prevalence of mixed over-/under-exposed images, which are not adequately addressed by existing methods. In response, this work introduces two enhanced variants of the SICE dataset: SICE_Grad and SICE_Mix, designed to better represent these complexities. The second challenge is the scarcity of suitable low-light video datasets for training and testing. To address this, the paper introduces the Night Wenzhou dataset, a large-scale, high-resolution video collection that features challenging fast-moving aerial scenes and streetscapes with varied illuminations and degradation. This study also conducts an extensive analysis of key techniques and performs comparative experiments using the proposed and current benchmark datasets. The survey concludes by highlighting emerging applications, discussing unresolved challenges, and suggesting future research directions within the LLIE community. The datasets are available at https://github.com/ShenZheng2000/LLIE_Survey.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 59 of its 164 references that are in the map. First posted on arXiv 21 Dec 2022.

Builds on

59 of 164 references.

References · 59

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2015Variational Inference with Normalizing Flowscited by 2,161
  10. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  11. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  12. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
38 more
  1. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  2. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  3. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  4. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  5. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  6. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  7. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  8. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  9. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 271
  10. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  11. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  12. 2019An Underwater Image Enhancement Benchmark Dataset and Beyondcited by 250
  13. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  14. 2019Spatial Attentive Single-Image Deraining with a High Quality Real Rain Datasetcited by 192
  15. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  16. 2021Low-Light Image Enhancement with Normalizing Flowcited by 184
  17. 2018Getting to Know Low-light Images with The Exclusively Dark Datasetcited by 157
  18. 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
  19. 2020A Physics-based Noise Formation Model for Extreme Low-light Raw Denoisingcited by 138
  20. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  21. 2018Visual Semantic Navigation using Scene Priorscited by 127
  22. 2018DSFD: Dual Shot Face Detectorcited by 115
  23. 2017WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Imagescited by 112
  24. 2020DeepLPF: Deep Local Parametric Filters for Image Enhancementcited by 107
  25. 2021R2RNet: Low-light Image Enhancement via Real-low to Real-normal Networkcited by 106
  26. 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 92
  27. 2021Image-Adaptive YOLO for Object Detection in Adverse Weather Conditionscited by 85
  28. 2019UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environmentscited by 84
  29. 2019Single Image Deraining: From Model-Based to Data-Driven and Beyondcited by 77
  30. 2019Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Datasetcited by 65
  31. 2021Burst Image Restoration and Enhancementcited by 64
  32. 2021Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancementcited by 60
  33. 2019Handheld Mobile Photography in Very Low Lightcited by 56
  34. 2021Adaptive Unfolding Total Variation Network for Low-Light Image Enhancementcited by 55
  35. 2022Dancing under the stars: video denoising in starlightcited by 47
  36. 2022Abandoning the Bayer-Filter to See in the Darkcited by 40
  37. 2020Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain Mappingcited by 26
  38. 2018Deep Underwater Image Enhancementcited by 24

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 8; 2026: 3.

17 papers.

Sort:

By area:

  1. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 62
  2. 2025Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restorationcited by 27
  3. 2024You Only Need One Color Space: An Efficient Network for Low-light Image Enhancementcited by 24
  4. 2023Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognitioncited by 20
  5. 2025Brightness Perceiving for Recursive Low-Light Image Enhancementcited by 14
  6. 2023Learning from History: Task-agnostic Model Contrastive Learning for Image Restorationcited by 11
  7. 2023TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Raincited by 5
  8. 2024Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancementcited by 3
  9. 2025HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancementcited by 2
  10. 2023Zero-Shot Enhancement of Low-Light Image Based on Retinex Decompositioncited by 1
  11. 2025Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modelingcited by 1
  12. 2025DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Expertscited by 1
5 more
  1. 2026VCR: Variance-Driven Channel Recalibration for Robust Low-Light Enhancementcited by 1
  2. 2025RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillationcited by 0
  3. 2025Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noisecited by 0
  4. 2026Nighttime Hazy Image Enhancement via Progressively and Mutually Reinforcing Night-Haze Priorscited by 0
  5. 2026Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancementcited by 0