基于生成对抗网络的单图像超分辨率重建  

Single Image Super-Resolution Reconstruction Based on Generative Adversarial Network

作　　者：朱海琦 李宏[1] 李定文 李富[2] ZHU Haiqi;LI Hong;LI Dingwen;LI Fu(School of Electrical Information Engineering,Northeast Petroleum University,Daqing 163318,Heilongjiang Province,China;Drilling No.1 Company,Daqing Drilling Engineering Company,Daqing 163458,Heilongjiang Province,China)

机构地区：[1]东北石油大学电气信息工程学院,黑龙江大庆163318 [2]大庆钻探工程公司钻井一公司,黑龙江大庆163458

出　　处：《吉林大学学报（理学版）》2021年第6期1491-1498,共8页Journal of Jilin University:Science Edition

基　　金：国家重大科技专项基金(批准号:2017ZX05019-005);黑龙江省自然科学基金(批准号:LH2019F004).

摘　　要：针对当前卷积神经网络未能充分利用浅层特征信息,并难以捕获各特征通道间的依赖关系、丢失高频信息的问题,提出一种新的生成对抗网络用于图像超分辨率重建.首先,在生成器中引入WDSR-B残差块充分提取浅层特征信息;其次,将GCNet模块和像素注意力机制相结合加入到生成器和鉴别器中,学习各特征通道的重要程度和高频信息;最后,采用谱归一化代替不利于图像超分辨率的批规范化,减少计算开销,稳定训练.实验结果表明,该算法与其他经典算法相比能有效提高浅层特征信息的利用率,较好地重建出图像的细节信息和几何特征,提高超分辨率图像的质量.Aiming at the problem that the current convolutional neural network could not make full use of the shallow feature information,and it was difficult to capture the dependency between each feature channel,resulting in the loss of high-frequency information,we proposed a new generative adversarial network for image super-resolution reconstruction.Firstly,the WDSR-B residual block was introduced into the generator to fully extract the shallow feature information.Secondly,the GCNet module and pixel attention mechanism were combined into the generator and discriminator to learn the importance and high-frequency information of each feature channel.Finally,using spectral normalization instead of batch normalization that was not conducive to image super-resolution,and reduced computational overhead and stabilize training.Experimental results show that compared with other classical algorithms,the proposed algorithm can effectively improve the utilization of shallow feature information,better reconstruct the detailed information and geometric features of the image,and improve the quality of super-resolution images.

关 键 词：图像超分辨率 生成对抗网络 注意力机制 残差网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]