mlsanityData to 7 Oct 2026

LEDNet: Joint Low-light Enhancement and Deblurring in the Dark

arXiv 2202.03373 ↗First posted 7 Feb 2022eess.IV cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

Night photography typically suffers from both low light and blurring issues due to the dim environment and the common use of long exposure. While existing light enhancement and deblurring methods could deal with each problem individually, a cascade of such methods cannot work harmoniously to cope well with joint degradation of visibility and textures. Training an end-to-end network is also infeasible as no paired data is available to characterize the coexistence of low light and blurs. We address the problem by introducing a novel data synthesis pipeline that models realistic low-light blurring degradations. With the pipeline, we present the first large-scale dataset for joint low-light enhancement and deblurring. The dataset, LOL-Blur, contains 12,000 low-blur/normal-sharp pairs with diverse darkness and motion blurs in different scenarios. We further present an effective network, named LEDNet, to perform joint low-light enhancement and deblurring. Our network is unique as it is specially designed to consider the synergy between the two inter-connected tasks. Both the proposed dataset and network provide a foundation for this challenging joint task. Extensive experiments demonstrate the effectiveness of our method on both synthetic and real-world datasets.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

38 of 58 references.

References · 38

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2016Pyramid Scene Parsing Networkcited by 2,472
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  7. 2021Multi-Stage Progressive Image Restorationcited by 813
  8. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  9. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
  10. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  11. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  12. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
26 more
  1. 2018Learning to See in the Darkcited by 459
  2. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  3. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  4. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  5. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  6. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  7. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  8. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
  9. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  10. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  11. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 212
  12. 2017Video Frame Interpolation via Adaptive Separable Convolutioncited by 211
  13. 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 205
  14. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  15. 2020Deblurring by Realistic Blurringcited by 187
  16. 2020Human-Aware Motion Deblurringcited by 174
  17. 2015Learning a Convolutional Neural Network for Non-uniform Motion Blur Removalcited by 148
  18. 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
  19. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 143
  20. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  21. 2019Spatio-Temporal Filter Adaptive Network for Video Deblurringcited by 106
  22. 2020Blind Face Restoration via Deep Multi-scale Component Dictionariescited by 106
  23. 2016From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blurcited by 81
  24. 2021Adaptive Unfolding Total Variation Network for Low-Light Image Enhancementcited by 55
  25. 2021ARVo: Learning All-Range Volumetric Correspondence for Video Deblurringcited by 54
  26. 2019DAVANet: Stereo Deblurring with View Aggregationcited by 37

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 21; 2024: 18; 2025: 31; 2026: 21.

95 papers.

Sort:

By area:

  1. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  2. 2023Iterative Prompt Learning for Unsupervised Backlit Image Enhancementcited by 107
  3. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  4. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  5. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
  6. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 62
  7. 2024DarkIR: Robust Low-Light Image Restorationcited by 48
  8. 2024FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restorationcited by 37
  9. 2023WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfacescited by 34
  10. 2025JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restorationcited by 32
  11. 2023Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyondcited by 31
  12. 2025Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restorationcited by 27
38 more
  1. 2024NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Resultscited by 26
  2. 2024You Only Need One Color Space: An Efficient Network for Low-light Image Enhancementcited by 24
  3. 2023Empowering Low-Light Image Enhancer through Customized Learnable Priorscited by 22
  4. 2024Towards Real-world Event-guided Low-light Video Enhancement and Deblurringcited by 22
  5. 2022Real-World Deep Local Motion Deblurringcited by 20
  6. 2023Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognitioncited by 20
  7. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restorationcited by 18
  8. 2023Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Cameracited by 16
  9. 2024LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenescited by 16
  10. 2023LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusioncited by 15
  11. 2023FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Tablecited by 15
  12. 2025RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restorationcited by 15
  13. 2025URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restorationcited by 15
  14. 2023VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebookcited by 12
  15. 20243DEnhancer: Consistent Multi-View Diffusion for 3D Enhancementcited by 12
  16. 2022CuDi: Curve Distillation for Efficient and Controllable Exposure Adjustmentcited by 11
  17. 2023Similarity Min-Max: Zero-Shot Day-Night Domain Adaptationcited by 10
  18. 2023Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fieldscited by 9
  19. 2023Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Darkcited by 9
  20. 2025LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removalcited by 9
  21. 2023Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancementcited by 8
  22. 2025DSwinIR: Rethinking Window-based Attention for Image Restorationcited by 7
  23. 2026Low Light Image Enhancement Challenge at NTIRE 2026cited by 7
  24. 2023Adaptive Window Pruning for Efficient Local Motion Deblurringcited by 6
  25. 2025UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradationscited by 6
  26. 2026From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmarkcited by 6
  27. 2024PIE: Physics-inspired Low-light Enhancementcited by 5
  28. 2024AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradationscited by 5
  29. 2025GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancementcited by 5
  30. 2025UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancementcited by 5
  31. 2024Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE)cited by 4
  32. 2025Universal Image Restoration Pre-training via Masked Degradation Classificationcited by 4
  33. 2023Make Lossy Compression Meaningful for Low-Light Imagescited by 3
  34. 2023Decomposition Ascribed Synergistic Learning for Unified Image Restorationcited by 3
  35. 2023Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancementcited by 3
  36. 2024Benchmarking the Robustness of Panoptic Segmentation for Automated Drivingcited by 3
  37. 2024DAP-LED: Learning Degradation-Aware Priors with CLIP for Joint Low-light Enhancement and Deblurringcited by 3
  38. 2024UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptationcited by 3

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception
  2. 2025Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling
  3. 2025Seeing Beyond Haze: Generative Nighttime Image Dehazing
  4. 2024Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors
  5. 2024Rethinking Model Redundancy for Low-light Image Enhancement
  6. 2025Learning to See in the Extremely Dark
  7. 2026OmniLight: One Model to Rule All Lighting Conditions
  8. 2024LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Network