mlsanityData to 14 Oct 2026

Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning

arXiv 1904.05050 ↗First posted 10 Apr 2019cs.CVcited by 157

Not on the map. Why?

Abstract (arXiv)

Most deraining works focus on rain streaks removal but they cannot deal adequately with heavy rain images. In heavy rain, streaks are strongly visible, dense rain accumulation or rain veiling effect significantly washes out the image, further scenes are relatively more blurry, etc. In this paper, we propose a novel method to address these problems. We put forth a 2-stage network: a physics-based backbone followed by a depth-guided GAN refinement. The first stage estimates the rain streaks, the transmission, and the atmospheric light governed by the underlying physics. To tease out these components more reliably, a guided filtering framework is used to decompose the image into its low- and high-frequency components. This filtering is guided by a rain-free residue image --- its content is used to set the passbands for the two channels in a spatially-variant manner so that the background details do not get mixed up with the rain-streaks. For the second stage, the refinement stage, we put forth a depth-guided GAN to recover the background details failed to be retrieved by the first stage, as well as correcting artefacts introduced by that stage. We have evaluated our method against the state of the art methods. Extensive experiments show that our method outperforms them on real rain image data, recovering visually clean images with good details.

Key facts. Cited by 157 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 25; 2023: 23; 2024: 33; 2025: 38; 2026: 22.

157 papers.

Sort:

By area:

  1. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 244
  2. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  3. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  4. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 109
  5. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 92
  6. 2021Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priorscited by 82
  7. 2024Restoring Images in Adverse Weather Conditions via Histogram Transformercited by 73
  8. 2023GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditionscited by 62
  9. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 60
  10. 2022Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyondcited by 48
  11. 2021Zero-Shot Day-Night Domain Adaptation with a Physics Priorcited by 47
  12. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restorationcited by 47
38 more
  1. 2023Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streakscited by 45
  2. 2025Degradation-Aware Feature Perturbation for All-in-One Image Restorationcited by 41
  3. 2022Toward Real-world Single Image Deraining: A New Benchmark and Beyondcited by 40
  4. 2023From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removalcited by 39
  5. 2021Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translationcited by 36
  6. 2023Language-driven All-in-one Adverse Weather Removalcited by 36
  7. 2023Towards Unified Deep Image Deraining: A Survey and A New Benchmarkcited by 34
  8. 2022Not Just Streaks: Towards Ground Truth for Single Image Derainingcited by 31
  9. 2024PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructionscited by 31
  10. 2022Unsupervised Deraining: Where Contrastive Learning Meets Self-similaritycited by 30
  11. 2021CoMoGAN: continuous model-guided image-to-image translationcited by 27
  12. 2025Visual-Instructed Degradation Diffusion for All-in-One Image Restorationcited by 26
  13. 2021Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removalcited by 24
  14. 2024Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraintcited by 24
  15. 2024MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformerscited by 24
  16. 2025NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 22
  17. 2025Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Datacited by 21
  18. 2022Prior Knowledge Guided Unsupervised Domain Adaptationcited by 20
  19. 2024NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correctioncited by 20
  20. 2025WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restorationcited by 20
  21. 2021Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Priorcited by 18
  22. 2024Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restorationcited by 18
  23. 2024LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restorationcited by 18
  24. 2023Learning Distortion Invariant Representation for Image Restoration from A Causality Perspectivecited by 17
  25. 2025RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restorationcited by 15
  26. 2023Networks are Slacking Off: Understanding Generalization Problem in Image Derainingcited by 14
  27. 2024Sharing Key Semantics in Transformer Makes Efficient Image Restorationcited by 14
  28. 2025Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Visioncited by 14
  29. 2026NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 14
  30. 2024Learning Truncated Causal History Model for Video Restorationcited by 13
  31. 2024All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting Modelcited by 13
  32. 2024GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restorationcited by 13
  33. 2021RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Derainingcited by 12
  34. 2022Unsupervised Image Deraining: Optimization Model Driven Deep CNNcited by 12
  35. 2022RCRN: Real-world Character Image Restoration Network via Skeleton Extractioncited by 12
  36. 2023Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removalcited by 12
  37. 2023Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removalcited by 12
  38. 2026ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restorationcited by 12

50 most cited of 157 All 157 (JSON)