mlsanityData to 7 Oct 2026

Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation

arXiv 2510.09228 ↗First posted 10 Oct 2025cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Adverse weather conditions such as haze, rain, and snow significantly degrade the quality of images and videos, posing serious challenges to intelligent transportation systems (ITS) that rely on visual input. These degradations affect critical applications including autonomous driving, traffic monitoring, and surveillance. This survey presents a comprehensive review of image and video restoration techniques developed to mitigate weather-induced visual impairments. We categorize existing approaches into traditional prior-based methods and modern data-driven models, including CNNs, transformers, diffusion models, and emerging vision-language models (VLMs). Restoration strategies are further classified based on their scope: single-task models, multi-task/multi-weather systems, and all-in-one frameworks capable of handling diverse degradations. In addition, we discuss day and night time restoration challenges, benchmark datasets, and evaluation protocols. The survey concludes with an in-depth discussion on limitations in current research and outlines future directions such as mixed/compound-degradation restoration, real-time deployment, and agentic AI frameworks. This work aims to serve as a valuable reference for advancing weather-resilient vision systems in smart transportation environments. Lastly, to stay current with rapid advancements in this field, we will maintain regular updates of the latest relevant papers and their open-source implementations at https://github.com/ChaudharyUPES/A-comprehensive-review-on-Multi-weather-restoration

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 103 of its 273 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

103 of 273 references.

References · 103

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  3. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  4. 2021Multi-Stage Progressive Image Restorationcited by 813
  5. 2022Simple Baselines for Image Restorationcited by 701
  6. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  7. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  8. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  9. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  10. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  11. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  12. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 271
38 more
  1. 2020Multi-Scale Progressive Fusion Network for Single Image Derainingcited by 259
  2. 2022Vision Transformers for Single Image Dehazingcited by 255
  3. 2018Density-aware Single Image De-raining using a Multi-stream Dense Networkcited by 248
  4. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  5. 2020Multi-Scale Boosted Dehazing Network with Dense Feature Fusioncited by 229
  6. 2019GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazingcited by 227
  7. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  8. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  9. 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
  10. 2017Attentive Generative Adversarial Network for Raindrop Removal from a Single Imagecited by 204
  11. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 204
  12. 2017DesnowNet: Context-Aware Deep Network for Snow Removalcited by 200
  13. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197
  14. 2019Spatial Attentive Single-Image Deraining with a High Quality Real Rain Datasetcited by 192
  15. 2019Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learningcited by 157
  16. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  17. 2019FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimationcited by 128
  18. 2020A Model-driven Deep Neural Network for Single Image Rain Removalcited by 125
  19. 2020NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Imagescited by 108
  20. 2020Domain Adaptation for Image Dehazingcited by 108
  21. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  22. 2019Dense Haze: A benchmark for image dehazing with dense-haze and haze-free imagescited by 107
  23. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  24. 2018Gated Context Aggregation Network for Image Dehazing and Derainingcited by 89
  25. 2019Single Image Deraining: A Comprehensive Benchmark Analysiscited by 84
  26. 2021Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priorscited by 82
  27. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  28. 2018Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazingcited by 79
  29. 2020FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazingcited by 79
  30. 2021Spatially-Adaptive Image Restoration using Distortion-Guided Networkscited by 77
  31. 2019Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restorationcited by 73
  32. 2023RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priorscited by 73
  33. 2019A General Decoupled Learning Framework for Parameterized Image Operatorscited by 72
  34. 2024Complexity Experts are Task-Discriminative Learners for Any Image Restorationcited by 72
  35. 2021Invertible Denoising Network: A Light Solution for Real Noise Removalcited by 68
  36. 2021From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Datacited by 68
  37. 2018I-HAZE: a dehazing benchmark with real hazy and haze-free indoor imagescited by 64
  38. 2018Lightweight Pyramid Networks for Image Derainingcited by 64

50 most cited of 103 All 103 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RIRF: Reasoning Image Restoration Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VLM-Augmented Degradation Modeling for Image Restoration Under Adverse Weather Conditions
  2. 2025DA2Diff: Exploring Degradation-aware Adaptive Diffusion Priors for All-in-One Weather Restoration
  3. 2023WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models
  4. 2026Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data
  5. 2026ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness
  6. 2025From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance
  7. 2026LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation Resilience
  8. 2025Object detection in adverse weather conditions for autonomous vehicles using Instruct Pix2Pix