用傅里叶令牌插件提升图像超分辨率效率，轻量且全局感知。
FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution
- 基于傅里叶变换与乘法操作构建全局感受野的插件模块
- 在x4放大下平均提升0.34dB PSNR，参数和计算量仅增加0.6%与1.5%
- 适合对轻量高效超分辨率有需求的工程部署场景
图像超分辨率旨在将低分辨率图像恢复为高分辨率图像，提升效率是核心挑战。现有方法如卷积和窗口式Transformer受限于局部感受野，难以在极低计算成本下实现高效重建。本文受卷积定理启发，提出一种基于傅里叶令牌的插件模块FourierSR，通过傅里叶变换与乘法操作实现全局信息建模，避免传统令牌混合技术在插件化应用中的不稳定性与效率问题。相比传统方法，FourierSR仅依赖傅里叶变换与乘法，显著降低复杂度。实验表明，在Manga109数据集x4缩放下，作为即插即用模块可为现有高效超分辨率方法带来平均0.34dB的PSNR提升，同时参数量和计算量仅增加原大小的0.6%和1.5%。代码将在接受后发布。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。