多尺度残差网络的单幅图像超分辨率重建  

Sigle Image Super-Resolution Reconstruction Based on Multi-scale Residual Network

作　　者：李现国[1] 冯欣欣 李建雄[1] LI Xianguo;FENG Xinxin;LI Jianxiong(School of Electronics and Information Engineering,Tiangong University,Tianjin 300387,China)

机构地区：[1]天津工业大学电子与信息工程学院,天津300387

出　　处：《计算机工程与应用》2021年第7期215-221,共7页Computer Engineering and Applications

基　　金：天津市重点研发计划科技支撑重点项目(18YFZCGX00930)。

摘　　要：针对目前提高图像分辨率的卷积神经网络存在的特征提取尺度单一以及梯度消失等问题,提出了多尺度残差网络的单幅图像超分辨率重建方法。采用多尺度特征提取和特征信息融合,解决了对图像细节特征提取不够充分的问题;将局部残差学习和全局残差学习相结合,提高了卷积神经网络信息流传播的效率,减轻了梯度消失现象。在Set5、Set14和BSD100等常用测试集上进行了实验,该方法的实验结果均优于其他5种方法,相比于SRCNN方法,平均PSNR提升了0.74 dB,平均SSIM提升了0.0143 dB;相比于VDSR方法,平均PSNR提升了0.12 dB,平均SSIM提升了0.0025 dB。Super-resolution reconstruetion methods based on Convolutional Neural Network(CNN)are confronting the problems of small receptive field,single feature extraction scale and disappearing of gradient information.In order to solve these problems,a single image super-resolution reconstruction method is proposed based on multi-scale residual network.By using multi-scale feature extraction and feature information fusion,the problem of insufficient image feature extraction is solved.The combination of local residual learning and global residual learning improves the efficiency of information flow and greatly reduces the phenomenon of gradient disappearance.Experiments are carried out on common test sets such as Set5,Set14 and BSD100,the experimental results of the proposed method are higher than the results of five comparison methods.Compared with the SRCNN,the average PSNR is improved by 0.74 dB and the average SSIM is improved by 0.0143 dB.Compared with the VDSR,the average PSNR is improved by 0.12 dB and the average SSIM is improved by 0.0025 dB.

关 键 词：图像超分辨率重建 卷积神经网络 残差学习 多尺度特征 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]