基于多分辨率特征融合的任意尺度图像超分辨率重建  

Super-Resolution Reconstruction of Arbitrary Scale Images Based on Multi-Resolution Feature Fusion

作　　者：范文卓 吴涛 许俊平[2] 李庆庆 张建林[2] 李美惠 魏宇星[2] FAN Wenzhuo;WU Tao;XU Junping;LI Qingqing;ZHANG Jianlin;LI Meihui;WEI Yuxing(School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 101408,China;Key Laboratory of Beam Control,Institute of Optics and Electronics,Chinese Academy of Sciences,Chengdu 610207,China)

机构地区：[1]中国科学院大学电子电气与通信工程学院,北京101408 [2]中国科学院光电技术研究所光束控制重点实验室,成都610207

出　　处：《计算机工程》2023年第9期217-225,共9页Computer Engineering

基　　金：国家自然科学基金青年基金(62101529)。

摘　　要：传统深度学习的图像超分辨率重建网络仅在固定分辨率上提取特征,存在无法综合高级语义信息、只能以特定尺度因子重建图像、泛化能力较弱、网络参数量较大等问题。提出一种基于多分辨率特征融合的任意尺度图像超分辨率重建算法MFSR。在多分辨率特征融合编码阶段设计多分辨率特征提取模块以提取不同分辨率特征,通过构建双重注意力模块增强网络特征提取能力,使不同分辨率特征之间进行充分交互,以获取信息丰富的融合特征图。在图像重建阶段利用多层感知机对融合特征图进行解码,实现任意尺度的图像超分辨率重建。实验结果表明,在Set5数据集上分别以尺度因子2、3、4、6、8进行测试,所提算法的峰值信噪比分别为38.62、34.70、32.41、28.96、26.62 dB,模型参数量为0.72×106,在大幅减少参数量的同时能保持重建质量,可以实现任意尺度的图像超分辨率重建,性能优于SRCNN、VDSR、EDSR等主流算法。Traditional deep learning image super-resolution reconstruction network only extracts features at a fixed resolution and cannot integrate advanced semantic information.The challenges include difficulties integrating advanced semantic information,reconstructing images with specific scale factors,limited generalization capability,and managing an excessive number of network parameters.An arbitrary scale image super-resolution reconstruction algorithm based on multi-resolution feature fusion is proposed,termed as MFSR.In the phase of multi-resolution feature fusion encoding,a multi-resolution feature extraction module is designed to extract different resolution features.A dual attention module is constructed to enhance the network feature extraction ability.The information-rich fused feature map is obtained by fully interacting with different resolution features.In the phase of image reconstruction,the fused feature map is decoded by a multi-layer perception machine to realize a super-resolution image at any scale.The experimental results indicate that tests were conducted on the Set5 data set with scaling factors of 2,3,4,6,8,and the Peak Signal-to-Noise Ratios(PSNR)of the proposed algorithm were 38.62,34.70,32.41,28.96,and 26.62 dB,respectively.The model parameters correspond to 0.72×106,which significantly reduce the number of parameters,maintain the reconstruction quality,and realize super-resolution image reconstruction at any scale.Furthermore,the model can realize better performance than mainstream algorithms,such as SRCNN,VDSR,and EDSR.

关 键 词：多分辨率特征融合 超分辨率重建 任意尺度 双重注意力 特征交互 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]