mlsanityData to 14 Oct 2026

Fourier-Guided Attention Upsampling for Image Super-Resolution

arXiv 2508.10616 ↗First posted 14 Aug 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose Frequency-Guided Attention (FGA), a lightweight upsampling module for single image super-resolution. Conventional upsamplers, such as Sub-Pixel Convolution, are efficient but frequently fail to reconstruct high-frequency details and introduce aliasing artifacts. FGA addresses these issues by integrating (1) a Fourier feature-based Multi-Layer Perceptron (MLP) for positional frequency encoding, (2) a cross-resolution Correlation Attention Layer for adaptive spatial alignment, and (3) a frequency-domain L1 loss for spectral fidelity supervision. Adding merely 0.3M parameters, FGA consistently enhances performance across five diverse super-resolution backbones in both lightweight and full-capacity scenarios. Experimental results demonstrate average PSNR gains of 0.12~0.14 dB and improved frequency-domain consistency by up to 29%, particularly evident on texture-rich datasets. Visual and spectral evaluations confirm FGA's effectiveness in reducing aliasing and preserving fine details, establishing it as a practical, scalable alternative to traditional upsampling methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 65 references that are in the map. First posted on arXiv 14 Aug 2025.

Builds on

42 of 65 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2013Describing Textures in the Wildcited by 2,125
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  8. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  9. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  10. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  12. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
30 more
  1. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  2. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  3. 2020Pre-Trained Image Processing Transformercited by 893
  4. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
  5. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  6. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  7. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  8. 2022Activating More Pixels in Image Super-Resolution Transformercited by 438
  9. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
  10. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 329
  11. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  12. 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
  13. 2019Residual Non-local Attention Networks for Image Restorationcited by 236
  14. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  15. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 181
  16. 2018Non-Local Recurrent Network for Image Restorationcited by 160
  17. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  18. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  19. 2022Cross Aggregation Transformer for Image Restorationcited by 92
  20. 2021Fourier Space Losses for Efficient Perceptual Image Super-Resolutioncited by 73
  21. 2020Learning A Single Network for Scale-Arbitrary Super-Resolutioncited by 66
  22. 2021On Efficient Transformer-Based Image Pre-training for Low-Level Visioncited by 64
  23. 2024DRCT: Saving Image Super-resolution away from Information Bottleneckcited by 40
  24. 2022SAPA: Similarity-Aware Point Affiliation for Feature Upsamplingcited by 32
  25. 2022FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsamplingcited by 25
  26. 2019DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factorscited by 24
  27. 2023WaveMixSR: A Resource-efficient Neural Network for Image Super-resolutioncited by 10
  28. 2023Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Contextcited by 8
  29. 2019Adaptive Transform Domain Image Super-resolution Via Orthogonally Regularized Deep Networkscited by 6
  30. 2023Multi-Depth Branch Network for Efficient Image Super-Resolutioncited by 4

Built on by

Not cited yet.