SRResNet Performance Enhancement Using Patch Inputs and Partial Convolution-Based Padding

作     者：Safi Ullah Seong-Ho Song 

作者机构：Division of SoftwareHallym University1 Hallymdaehak-gilChuncheonGangwon-doKorea Department of Information TechnologyUniversity of GujratJalalpur Jattan RoadGujratPakistan 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第74卷第2期

页      面：2999-3014页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：HallymUniversity Research Fund HRF-202104-004 

主　　题：Single image super-resolution SRResNet patch inputs zero padding partial convolution based padding 

摘      要：Due to highly underdetermined nature of Single Image Super-Resolution(SISR)problem,deep learning neural networks are required to be more deeper to solve the problem *** of deep neural networks successful in the Super-Resolution(SR)problem is ResNet which can render the capability of deeper networks with the help of skip ***,zero padding(ZP)scheme in the network restricts benefits of skip connections in SRResNet and its performance as the ratio of the number of pure input data to that of zero padded data *** this *** consider the ResNet with Partial Convolution based Padding(PCP)instead of ZP to solve SR *** training of deep neural networks using patch images is advantageous in many aspects such as the number of training image data and network complexities,patch image based SR performance is compared with single full image based *** experimental results show that patch based SRResNet SR results are better than single full image based ones and the performance of deep SRResNet with PCP is better than the one with ZP.