mlsanityData to 7 Oct 2026

Clearing the Skies: A deep network architecture for single-image rain removal

arXiv 1609.02087 ↗First posted 7 Sep 2016cs.CVcited by 136

Not on the map. Why?

Abstract (arXiv)

We introduce a deep network architecture called DerainNet for removing rain streaks from an image. Based on the deep convolutional neural network (CNN), we directly learn the mapping relationship between rainy and clean image detail layers from data. Because we do not possess the ground truth corresponding to real-world rainy images, we synthesize images with rain for training. In contrast to other common strategies that increase depth or breadth of the network, we use image processing domain knowledge to modify the objective function and improve deraining with a modestly-sized CNN. Specifically, we train our DerainNet on the detail (high-pass) layer rather than in the image domain. Though DerainNet is trained on synthetic data, we find that the learned network translates very effectively to real-world images for testing. Moreover, we augment the CNN framework with image enhancement to improve the visual results. Compared with state-of-the-art single image de-raining methods, our method has improved rain removal and much faster computation time after network training.

Key facts. Cited by 136 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 26; 2023: 28; 2024: 28; 2025: 18; 2026: 11.

136 papers.

Sort:

By area:

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  2. 2021Multi-Stage Progressive Image Restorationcited by 813
  3. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  4. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 236
  5. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  6. 2022Deep Generalized Unfolding Networks for Image Restorationcited by 119
  7. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 91
  8. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  9. 2021Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priorscited by 82
  10. 2021Spatially-Adaptive Image Restoration using Distortion-Guided Networkscited by 77
  11. 2021On Efficient Transformer-Based Image Pre-training for Low-Level Visioncited by 64
  12. 2021Structure-Preserving Deraining with Residue Channel Prior Guidancecited by 63
38 more
  1. 2023GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditionscited by 62
  2. 2021Unpaired Deep Image Deraining Using Dual Contrastive Learningcited by 60
  3. 2024FreqMamba: Viewing Mamba from a Frequency Perspective for Image Derainingcited by 57
  4. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
  5. 2022Toward Real-world Single Image Deraining: A New Benchmark and Beyondcited by 40
  6. 2024U-shaped Vision Mamba for Single Image Dehazingcited by 40
  7. 2021Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translationcited by 36
  8. 2025MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restorationcited by 36
  9. 2023Towards Unified Deep Image Deraining: A Survey and A New Benchmarkcited by 34
  10. 2023KBNet: Kernel Basis Network for Image Restorationcited by 33
  11. 2021Robust Representation Learning with Feedback for Single Image Derainingcited by 32
  12. 2024FourierMamba: Fourier Learning Integration with State Space Models for Image Derainingcited by 32
  13. 2021Semi-Supervised Video Deraining with Dynamical Rain Generatorcited by 31
  14. 2022Not Just Streaks: Towards Ground Truth for Single Image Derainingcited by 31
  15. 2021Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Frameworkcited by 30
  16. 2022Unsupervised Deraining: Where Contrastive Learning Meets Self-similaritycited by 30
  17. 2023ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Renderingcited by 28
  18. 2022DRT: A Lightweight Single Image Deraining Recursive Transformercited by 26
  19. 2021Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removalcited by 24
  20. 2024Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restorationcited by 20
  21. 2021Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Priorcited by 18
  22. 2022Multi-scale frequency separation network for image deblurringcited by 18
  23. 2022Magic ELF: Image Deraining Meets Association Learning and Transformercited by 17
  24. 2022Restoring Vision in Hazy Weather with Hierarchical Contrastive Learningcited by 17
  25. 2023Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restorationcited by 17
  26. 2023HQ-50K: A Large-scale, High-quality Dataset for Image Restorationcited by 15
  27. 2023Mixed Hierarchy Network for Image Restorationcited by 14
  28. 2023Networks are Slacking Off: Understanding Generalization Problem in Image Derainingcited by 14
  29. 2023Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditionscited by 14
  30. 2021Efficient and Accurate Multi-scale Topological Network for Single Image Dehazingcited by 13
  31. 2022Snow Mask Guided Adaptive Residual Network for Image Snow Removalcited by 13
  32. 2021RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Derainingcited by 12
  33. 2025Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Derainingcited by 11
  34. 2025Intra and Inter Parser-Prompted Transformers for Effective Image Restorationcited by 10
  35. 2025EAMamba: Efficient All-Around Vision State Space Model for Image Restorationcited by 10
  36. 2022GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removalcited by 9
  37. 2023Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flowcited by 9
  38. 2023Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Darkcited by 9

50 most cited of 136 All 136 (JSON)