FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912763025031168 |
|---|---|
| author | Li, Wenjie Guo, Heng Hou, Yuefeng Ma, Zhanyu |
| author_facet | Li, Wenjie Guo, Heng Hou, Yuefeng Ma, Zhanyu |
| contents | Image super-resolution (SR) aims to recover low-resolution images to high-resolution images, where improving SR efficiency is a high-profile challenge. However, commonly used units in SR, like convolutions and window-based Transformers, have limited receptive fields, making it challenging to apply them to improve SR under extremely limited computational cost. To address this issue, inspired by modeling convolution theorem through token mix, we propose a Fourier token-based plugin called FourierSR to improve SR uniformly, which avoids the instability or inefficiency of existing token mix technologies when applied as plug-ins. Furthermore, compared to convolutions and windows-based Transformers, our FourierSR only utilizes Fourier transform and multiplication operations, greatly reducing complexity while having global receptive fields. Experimental results show that our FourierSR as a plug-and-play unit brings an average PSNR gain of 0.34dB for existing efficient SR methods on Manga109 test set at the scale of x4, while the average increase in the number of Params and FLOPs is only 0.6% and 1.5% of original sizes. We will release our codes upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10043 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution Li, Wenjie Guo, Heng Hou, Yuefeng Ma, Zhanyu Computer Vision and Pattern Recognition Image super-resolution (SR) aims to recover low-resolution images to high-resolution images, where improving SR efficiency is a high-profile challenge. However, commonly used units in SR, like convolutions and window-based Transformers, have limited receptive fields, making it challenging to apply them to improve SR under extremely limited computational cost. To address this issue, inspired by modeling convolution theorem through token mix, we propose a Fourier token-based plugin called FourierSR to improve SR uniformly, which avoids the instability or inefficiency of existing token mix technologies when applied as plug-ins. Furthermore, compared to convolutions and windows-based Transformers, our FourierSR only utilizes Fourier transform and multiplication operations, greatly reducing complexity while having global receptive fields. Experimental results show that our FourierSR as a plug-and-play unit brings an average PSNR gain of 0.34dB for existing efficient SR methods on Manga109 test set at the scale of x4, while the average increase in the number of Params and FLOPs is only 0.6% and 1.5% of original sizes. We will release our codes upon acceptance. |
| title | FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.10043 |