文献类型：期刊文献

英文题名：Dual attention transformer with adaptive frequency enhancement for real-world Chinese-English scene text image super-resolution

作者：Liu, Yanbin[1];Shi, Qin[1];Zhu, Ziming[1];Ling, Xiaofeng[1];Zhu, Yu[1,2]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Engn Res Ctr Internet Things Resp Med, Shanghai 200032, Peoples R China

年份：2025

卷号：31

期号：5

外文期刊名：MULTIMEDIA SYSTEMS

收录：;EI(收录号：20253419045179);WOS:【SCI-EXPANDED(收录号:WOS:001599777500003)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant (62170110, 62476088), and the Shanghai Automotive Industry Science and Technology Development Foundation under Grant 2304.

语种：英文

外文关键词：Real-world text image super-resolution; Dual-branch network; Dense and sparse window attention; Spatial-channel interaction; Adaptive frequency enhancement

摘要：Scene text image super-resolution (STISR) has achieved remarkable performance on the pure English dataset, TextZoom. Nevertheless, existing STISR models are primarily designed for fixed-size English text images, limiting their ability to reconstruct structurally complex characters like Chinese characters. Due to the squared computational complexity of standard self-attention, existing methods usually restrict the self-attention calculation within local windows, leading to a limited receptive field. In this paper, we propose a dual attention transformer with adaptive frequency enhancement (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$DA<^>2FE$$\end{document}) model which alternates between two complementary window attention mechanisms. Specifically, dense window attention (DWA) facilitates interactions between neighboring tokens, which is beneficial for learning local features. Sparse window attention (SWA) establishes associations between spaced tokens, enabling effective global information extraction. Additionally, we incorporate a parallel depth-wise convolution (DWConv) branch to establish cross-window relations. Subsequently, a spatial-channel interaction module is employed to facilitate the bi-directional interaction between the window attention branch and the DWConv branch. Furthermore, we design a feed-forward network with adaptive frequency enhancement (FFN-AFE), which introduces a learnable quantitative matrix in the frequency domain to adaptively select and enhance significant frequency information. Finally, the output features from multiple layers are aggregated and refined to provide more comprehensive information for SR reconstruction. Comparative experiments with advanced methods on the Real-CE dataset demonstrate our superior performance in terms of objective indicators and subjective visual results for both \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2\times $$\end{document} and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$4\times $$\end{document} STISR tasks. Furthermore, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$DA<^>2FE$$\end{document} exhibits excellent results on natural image super-resolution datasets, further demonstrating its broad applicability.