mlsanityData to 7 Oct 2026

Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution

arXiv 2407.16232 ↗First posted 23 Jul 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Recently, window-based attention methods have shown great potential for computer vision tasks, particularly in Single Image Super-Resolution (SISR). However, it may fall short in capturing long-range dependencies and relationships between distant tokens. Additionally, we find that learning on spatial domain does not convey the frequency content of the image, which is a crucial aspect in SISR. To tackle these issues, we propose a new Channel-Partitioned Attention Transformer (CPAT) to better capture long-range dependencies by sequentially expanding windows along the height and width of feature maps. In addition, we propose a novel Spatial-Frequency Interaction Module (SFIM), which incorporates information from spatial and frequency domains to provide a more comprehensive information from feature maps. This includes information about the frequency content and enhances the receptive field across the entire image. Experimental findings show the effectiveness of our proposed modules and architecture. In particular, CPAT surpasses current state-of-the-art methods by up to 0.31dB at x2 SR on Urban100.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 43 of its 69 references that are in the map. First posted on arXiv 23 Jul 2024.

Builds on

43 of 69 references.

References · 43

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  7. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  8. 2015Spatial Transformer Networkscited by 1,423
  9. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  10. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  11. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  12. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
31 more
  1. 2020Pre-Trained Image Processing Transformercited by 891
  2. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  3. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  4. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  5. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  6. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  7. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  8. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  9. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
  10. 2022TransGeo: Transformer Is All You Need for Cross-view Image Geo-localizationcited by 166
  11. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  12. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  13. 2020Interpreting Super-Resolution Networks with Local Attribution Mapscited by 136
  14. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  15. 2022Cross Aggregation Transformer for Image Restorationcited by 92
  16. 2021LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyondcited by 88
  17. 2021On Efficient Transformer-Based Image Pre-training for Low-Level Visioncited by 64
  18. 2023Omni Aggregation Networks for Lightweight Image Super-Resolutioncited by 62
  19. 2017Learnable pooling with Context Gating for video classificationcited by 58
  20. 2015Seven ways to improve example-based single image super resolutioncited by 51
  21. 2016Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognitioncited by 46
  22. 2022End-to-End Transformer Based Model for Image Captioningcited by 37
  23. 2022Revisiting RCAN: Improved Training for Image Super-Resolutioncited by 32
  24. 2023VQ3D: Learning a 3D-Aware Generative Model on ImageNetcited by 32
  25. 2020Image Captioning through Image Transformercited by 29
  26. 2022Fast and Memory-Efficient Network Towards Efficient Image Super-Resolutioncited by 27
  27. 2022Self-Calibrated Efficient Transformer for Lightweight Super-Resolutioncited by 20
  28. 2023MOST: Multiple Object localization with Self-supervised Transformers for object discoverycited by 17
  29. 2021A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentationcited by 12
  30. 2021FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transformcited by 11
  31. 2022LocATe: End-to-end Localization of Actions in 3D with Transformerscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025VSRM: A Robust Mamba-Based Framework for Video Super-Resolutioncited by 5
  2. 2026SAT: Selective Aggregation Transformer for Image Super-Resolutioncited by 2
  3. 20252D Representation for Unguided Single-View 3D Super-Resolution in Real-Timecited by 0
  4. 2026Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling and Downscaling Processcited by 0
  5. 2026FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolutioncited by 0