mlsanityData to 14 Oct 2026

Restormer: Efficient Transformer for High-Resolution Image Restoration

arXiv 2111.09881 ↗First posted 18 Nov 2021cs.CVcited by 1,627

Not on the map. Why?

Cited by 170 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural architectures, Transformers, have shown significant performance gains on natural language and high-level vision tasks. While the Transformer model mitigates the shortcomings of CNNs (i.e., limited receptive field and inadaptability to input content), its computational complexity grows quadratically with the spatial resolution, therefore making it infeasible to apply to most image restoration tasks involving high-resolution images. In this work, we propose an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images. Our model, named Restoration Transformer (Restormer), achieves state-of-the-art results on several image restoration tasks, including image deraining, single-image motion deblurring, defocus deblurring (single-image and dual-pixel data), and image denoising (Gaussian grayscale/color denoising, and real image denoising). The source code and pre-trained models are available at https://github.com/swz30/Restormer.

Key facts. Cited by 1,627 papers in the map (data through 14 Oct 2026). Builds on 81 of its 109 references that are in the map. First posted on arXiv 18 Nov 2021.

Builds on

81 of 109 references.

References · 81

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2016Layer Normalizationcited by 5,669
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
38 more
  1. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  2. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  3. 2017Non-local Neural Networkscited by 2,293
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  7. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  8. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  9. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  10. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  12. 2021Transformers in Vision: A Surveycited by 1,013
  13. 2020Pre-Trained Image Processing Transformercited by 893
  14. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  15. 2021Multi-Stage Progressive Image Restorationcited by 816
  16. 2018Self-Attention Generative Adversarial Networkscited by 809
  17. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  18. 2016Language Modeling with Gated Convolutional Networkscited by 702
  19. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  20. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  21. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  22. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 367
  23. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 362
  24. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 352
  25. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 347
  26. 2018Scale-recurrent Network for Deep Image Deblurringcited by 333
  27. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  28. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 312
  29. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  30. 2019Progressive Image Deraining Networks: A Better and Simpler Baselinecited by 272
  31. 2020Multi-Scale Progressive Fusion Network for Single Image Derainingcited by 260
  32. 2018Density-aware Single Image De-raining using a Multi-stream Dense Networkcited by 248
  33. 2019Residual Non-local Attention Networks for Image Restorationcited by 236
  34. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 213
  35. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  36. 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 206
  37. 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
  38. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 123; 2023: 274; 2024: 451; 2025: 434; 2026: 338.

1,627 papers.

Sort:

By area:

  1. 2022Simple Baselines for Image Restorationcited by 708
  2. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  3. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  4. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 352
  5. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 257
  6. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 255
  7. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 231
  8. 2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 223
  9. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  10. 2023Learning A Sparse Transformer Network for Effective Image Derainingcited by 205
  11. 2023OpenAGI: When LLM Meets Domain Expertscited by 197
  12. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 183
38 more
  1. 2024A Survey on Diffusion Models for Inverse Problemscited by 180
  2. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  3. 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 165
  4. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 165
  5. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  6. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  7. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
  8. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  9. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 140
  10. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 127
  11. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  12. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
  13. 2024Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformerscited by 118
  14. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 114
  15. 2021Event-Based Fusion for Motion Deblurring with Cross-modal Attentioncited by 113
  16. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
  17. 2021U-shape Transformer for Underwater Image Enhancementcited by 112
  18. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 111
  19. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 111
  20. 2022AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensingcited by 110
  21. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 110
  22. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 109
  23. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 100
  24. 2023Equivariant Multi-Modality Image Fusioncited by 99
  25. 2024MambaIRv2: Attentive State Space Restorationcited by 94
  26. 2022Cross Aggregation Transformer for Image Restorationcited by 92
  27. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 92
  28. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  29. 2023Hierarchical Integration Diffusion Model for Realistic Image Deblurringcited by 88
  30. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 86
  31. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  32. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Modelscited by 86
  33. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  34. 2024Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusioncited by 84
  35. 2021Intriguing Findings of Frequency Selection for Image Deblurringcited by 81
  36. 2022You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correctioncited by 81
  37. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  38. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 77

50 most cited of 1,627 All 1,627 (JSON)