通信学报2025，Vol.46Issue(4)：144-159,16.DOI:10.11959/j.issn.1000-436x.2025059
基于多域信息增强的轻量级图像超分辨率网络
Lightweight image super-resolution network based on muti-domain information enhancement
摘要
Abstract
Aiming to solve the problems that the reconstruction capability of single-domain features was limited and deep convolutional neural networks used in existing single-image super-resolution reconstruction tasks were difficult to deploy on mobile terminals due to the large number of parameters and high computational requirements,a lightweight image super-resolution network based on multi-domain information enhancement was proposed.Initiating from three di-mensions,a set of innovative techniques had been developed,including multi-path large kernel feature extraction in the spatial domain,local information enhancement attention,frequency-domain feature enhancement through frequency splitting,and transformation-domain prior-guided high-frequency feature simulation.By processing information across different feature domains,both global and local low-frequency and high-frequency features were optimized,significantly improving the model's performance in detail recovery and image reconstruction.Extensive experimental comparisons and analyses with the existing advanced algorithms on the recognized benchmark datasets demonstrate that the proposed network model can achieve remarkable reconstruction results while enjoying a high trade-off between performance and efficiency.关键词
计算机视觉/超分辨率/多域信息增强/注意力/轻量级Key words
computer vision/super resolution/multi-domain information enhancement/attention/lightweight分类
计算机与自动化引用本文复制引用
寇旗旗,刘规,江鹤,陈亮亮,程德强..基于多域信息增强的轻量级图像超分辨率网络[J].通信学报,2025,46(4):144-159,16.基金项目
国家自然科学基金资助项目(No.52204177,No.52304182) （No.52204177,No.52304182）
济宁市重点研发基金资助项目(No.2021KJHZ013,No.2023KJHZ007) The National Natural Science Foundation of China(No.52204177,No.52304182),The Key Research and Devel-opment Program of Jining City(No.2021KJHZ013,No.2023KJHZ007) （No.2021KJHZ013,No.2023KJHZ007）
