mlsanityData to 14 Oct 2026

SwinIR: Image Restoration Using Swin Transformer

arXiv 2108.10257 ↗First posted 23 Aug 2021eess.IV cs.CVcited by 1,887

Not on the map. Why?

Cited by 265 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14~0.45dB, while the total number of parameters can be reduced by up to 67%.

Key facts. Cited by 1,887 papers in the map (data through 14 Oct 2026). Builds on 65 of its 98 references that are in the map. First posted on arXiv 23 Aug 2021.

Builds on

65 of 98 references.

References · 65

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  8. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  10. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  11. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  12. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
38 more
  1. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  2. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  3. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  4. 2020Pre-Trained Image Processing Transformercited by 893
  5. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  6. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  7. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  8. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  9. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  10. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  11. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  12. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  13. 2021Early Convolutions Help Transformers See Bettercited by 396
  14. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  15. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  16. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 329
  17. 2019On the Relationship between Self-Attention and Convolutional Layerscited by 300
  18. 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
  19. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 264
  20. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  21. 2019Residual Non-local Attention Networks for Image Restorationcited by 236
  22. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 228
  23. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  24. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227
  25. 2018Deep Back-Projection Networks For Super-Resolutioncited by 225
  26. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  27. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 195
  28. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  29. 2018Residual Dense Network for Image Restorationcited by 181
  30. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  31. 2018Non-Local Recurrent Network for Image Restorationcited by 160
  32. 2019Feedback Network for Image Super-Resolutioncited by 155
  33. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  34. 2021Video Super-Resolution Transformercited by 121
  35. 2020Video Super-Resolution with Recurrent Structure-Detail Networkcited by 116
  36. 2019Frequency Separation for Real-World Super-Resolutioncited by 115
  37. 2018Neural Nearest Neighbors Networkscited by 98
  38. 2020Cross-Scale Internal Graph Neural Network for Image Super-Resolutioncited by 94

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 34; 2022: 236; 2023: 387; 2024: 456; 2025: 446; 2026: 328.

1,887 papers.

Sort:

By area:

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  2. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  3. 2022Simple Baselines for Image Restorationcited by 708
  4. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 583
  5. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  6. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  7. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  8. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  9. 2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 422
  10. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 365
  11. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 352
  12. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 320
38 more
  1. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 315
  2. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 302
  3. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  4. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 275
  5. 2022Vision Transformers for Single Image Dehazingcited by 260
  6. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 257
  7. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 255
  8. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 254
  9. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 246
  10. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 244
  11. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 238
  12. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 231
  13. 2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 223
  14. 2022VRT: A Video Restoration Transformercited by 220
  15. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
  16. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 218
  17. 2022Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Modelscited by 215
  18. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 211
  19. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  20. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 199
  21. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 183
  22. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 182
  23. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 170
  24. 2022Efficient Frequency Domain-based Transformers for High-Quality Image Deblurringcited by 165
  25. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  26. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  27. 2021Transformer for Single Image Super-Resolutioncited by 150
  28. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  29. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 140
  30. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  31. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  32. 2021Video Frame Interpolation Transformercited by 123
  33. 2022UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormercited by 116
  34. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  35. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 114
  36. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 113
  37. 2021U-shape Transformer for Underwater Image Enhancementcited by 112
  38. 2024AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulationcited by 111

50 most cited of 1,887 All 1,887 (JSON)