mlsanityData to 7 Oct 2026

Vision Transformers for Single Image Dehazing

arXiv 2204.03883 ↗First posted 8 Apr 2022cs.CVcited by 255

Not on the map. Why?

Cited by 23 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image dehazing is a representative low-level vision task that estimates latent haze-free images from hazy images. In recent years, convolutional neural network-based methods have dominated image dehazing. However, vision Transformers, which has recently made a breakthrough in high-level vision tasks, has not brought new dimensions to image dehazing. We start with the popular Swin Transformer and find that several of its key designs are unsuitable for image dehazing. To this end, we propose DehazeFormer, which consists of various improvements, such as the modified normalization layer, activation function, and spatial information aggregation scheme. We train multiple variants of DehazeFormer on various datasets to demonstrate its effectiveness. Specifically, on the most frequently used SOTS indoor set, our small model outperforms FFA-Net with only 25% #Param and 5% computational cost. To the best of our knowledge, our large model is the first method with the PSNR over 40 dB on the SOTS indoor set, dramatically outperforming the previous state-of-the-art methods. We also collect a large-scale realistic remote sensing dehazing dataset for evaluating the method's capability to remove highly non-homogeneous haze.

Key facts. Cited by 255 papers in the map (data through 7 Oct 2026). Builds on 60 of its 94 references that are in the map. First posted on arXiv 8 Apr 2022.

Builds on

60 of 94 references.

References · 60

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2016Layer Normalizationcited by 5,579
  10. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  11. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  12. 2022A ConvNet for the 2020scited by 3,545
38 more
  1. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  3. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2020Rethinking Attention with Performerscited by 1,584
  7. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  8. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  9. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  10. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  11. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  12. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  13. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  14. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  15. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  16. 2019Selective Kernel Networkscited by 401
  17. 2021Early Convolutions Help Transformers See Bettercited by 395
  18. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  19. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  20. 2022How Do Vision Transformers Work?cited by 305
  21. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 243
  22. 2020Multi-Scale Boosted Dehazing Network with Dense Feature Fusioncited by 229
  23. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  24. 2019GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazingcited by 227
  25. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  26. 2022UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learningcited by 182
  27. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 171
  28. 2018Densely Connected Pyramid Dehazing Networkcited by 145
  29. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  30. 2018Gated Fusion Network for Single Image Dehazingcited by 133
  31. 2021RegionViT: Regional-to-Local Attention for Vision Transformerscited by 126
  32. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  33. 2020NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Imagescited by 108
  34. 2020Domain Adaptation for Image Dehazingcited by 108
  35. 2019Dense Haze: A benchmark for image dehazing with dense-haze and haze-free imagescited by 107
  36. 2018O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor imagescited by 95
  37. 2021CAT: Cross Attention in Vision Transformercited by 92
  38. 2018Gated Context Aggregation Network for Image Dehazing and Derainingcited by 89

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 45; 2024: 74; 2025: 74; 2026: 55.

255 papers.

Sort:

By area:

  1. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 113
  2. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
  3. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 108
  4. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  5. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 91
  6. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  7. 2024Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Modelcited by 73
  8. 2024Restoring Images in Adverse Weather Conditions via Histogram Transformercited by 73
  9. 2023GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditionscited by 62
  10. 2024Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restorationcited by 60
  11. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
  12. 2023A Comparative Study of Image Restoration Networks for General Backbone Network Designcited by 56
38 more
  1. 2024Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategycited by 48
  2. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restorationcited by 46
  3. 2023Neural Degradation Representation Learning for All-In-One Image Restorationcited by 46
  4. 2023Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streakscited by 45
  5. 2024MaIR: A Locality- and Continuity-Preserving Mamba for Image Restorationcited by 43
  6. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
  7. 2024U-shaped Vision Mamba for Single Image Dehazingcited by 40
  8. 2023Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolutioncited by 39
  9. 2023Language-driven All-in-one Adverse Weather Removalcited by 36
  10. 2023Improving Image Restoration through Removing Degradations in Textual Representationscited by 36
  11. 2024Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazingcited by 32
  12. 2022Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removalcited by 28
  13. 2023Textual Prompt Guided Image Restorationcited by 27
  14. 2024Efficient Visual State Space Model for Image Deblurringcited by 27
  15. 2023TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusioncited by 26
  16. 2025Visual-Instructed Degradation Diffusion for All-in-One Image Restorationcited by 26
  17. 2024Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraintcited by 24
  18. 2023Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Priorcited by 22
  19. 2024NightHaze: Nighttime Image Dehazing via Self-Prior Learningcited by 22
  20. 2025From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspectivecited by 22
  21. 2025NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 22
  22. 2024Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restorationcited by 21
  23. 2024ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformercited by 20
  24. 2025WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restorationcited by 20
  25. 2024Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restorationcited by 19
  26. 2025Multi-Agent Image Restorationcited by 19
  27. 2023MixDehazeNet : Mix Structure Block For Image Dehazing Networkcited by 18
  28. 2023Mutual Information-driven Triple Interaction Network for Efficient Image Dehazingcited by 18
  29. 2023Frequency Compensated Diffusion Model for Real-scene Dehazingcited by 17
  30. 2024ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazingcited by 16
  31. 2024Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restorationcited by 15
  32. 2024HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenescited by 15
  33. 2024All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmarkcited by 14
  34. 2024RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazingcited by 14
  35. 2024Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solutioncited by 14
  36. 2022SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowingcited by 13
  37. 2022LKD-Net: Large Kernel Convolution Network for Single Image Dehazingcited by 13
  38. 2023Let Segment Anything Help Image Dehazecited by 13

50 most cited of 255 All 255 (JSON)