mlsanityData to 7 Oct 2026

Activating More Pixels in Image Super-Resolution Transformer

arXiv 2205.04437 ↗First posted 9 May 2022eess.IV cs.CVcited by 433

Not on the map. Why?

Cited by 70 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB. Codes and models are available at https://github.com/XPixelGroup/HAT.

Key facts. Cited by 433 papers in the map (data through 7 Oct 2026). Builds on 59 of its 78 references that are in the map. First posted on arXiv 9 May 2022.

Builds on

59 of 78 references.

References · 59

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  10. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  12. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
38 more
  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  2. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  3. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  6. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  7. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  8. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  9. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  10. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  11. 2020Pre-Trained Image Processing Transformercited by 891
  12. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  13. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  14. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  15. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  16. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  17. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  18. 2021Early Convolutions Help Transformers See Bettercited by 395
  19. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  20. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  21. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 333
  22. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  23. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  24. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  25. 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
  26. 2021Incorporating Convolution Designs into Visual Transformerscited by 248
  27. 2019Residual Non-local Attention Networks for Image Restorationcited by 236
  28. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  29. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  30. 2022VRT: A Video Restoration Transformercited by 219
  31. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  32. 2018Non-Local Recurrent Network for Image Restorationcited by 160
  33. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  34. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  35. 2020Interpreting Super-Resolution Networks with Local Attribution Mapscited by 136
  36. 2021Video Super-Resolution Transformercited by 120
  37. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  38. 2020Cross-Scale Internal Graph Neural Network for Image Super-Resolutioncited by 94

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 15; 2023: 62; 2024: 150; 2025: 130; 2026: 76.

433 papers.

Sort:

By area:

  1. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  2. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  3. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  4. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  5. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  6. 2023PromptIR: Prompting for All-in-One Blind Image Restorationcited by 113
  7. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  8. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  9. 2024MambaIRv2: Attentive State Space Restorationcited by 90
  10. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  11. 2022SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolutioncited by 67
  12. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 66
38 more
  1. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  2. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  3. 2024Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionarycited by 63
  4. 2023Omni Aggregation Networks for Lightweight Image Super-Resolutioncited by 62
  5. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  6. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  7. 2023A Comparative Study of Image Restoration Networks for General Backbone Network Designcited by 56
  8. 2023EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolutioncited by 56
  9. 2024Towards Realistic Data Generation for Real-World Super-Resolutioncited by 56
  10. 2023ResDiff: Combining CNN and Diffusion Model for Image Super-Resolutioncited by 53
  11. 2023Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolutioncited by 51
  12. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  13. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  14. 2024Frequency-Assisted Mamba for Remote Sensing Image Super-Resolutioncited by 47
  15. 2023Neural Degradation Representation Learning for All-In-One Image Restorationcited by 46
  16. 2024MaIR: A Locality- and Continuity-Preserving Mamba for Image Restorationcited by 43
  17. 2024BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modelingcited by 42
  18. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  19. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
  20. 2024DRCT: Saving Image Super-resolution away from Information Bottleneckcited by 40
  21. 2024NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Resultscited by 40
  22. 2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Datasetcited by 38
  23. 2023Improving Image Restoration through Removing Degradations in Textual Representationscited by 36
  24. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  25. 2023Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoisingcited by 35
  26. 2022Low-Light Video Enhancement with Synthetic Event Guidancecited by 33
  27. 2024RealViformer: Investigating Attention for Real-World Video Super-Resolutioncited by 33
  28. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  29. 2022Multi-scale Attention Network for Single Image Super-Resolutioncited by 29
  30. 2025Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Modelcited by 29
  31. 2023Recursive Generalization Transformer for Image Super-Resolutioncited by 28
  32. 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurringcited by 28
  33. 2023OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformercited by 26
  34. 2023Materialistic: Selecting Similar Materials in Imagescited by 26
  35. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 25
  36. 2025Progressive Focused Transformer for Single Image Super-Resolutioncited by 25
  37. 2026The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Reportcited by 25
  38. 2025Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Modelscited by 24

50 most cited of 433 All 433 (JSON)