Super-resolution Reconstruction Based on Capsule Generative Adversarial Network

International Journal of Advanced Network, Monitoring, and Controls

article

Ziyi Wu¹  Hongge Yao¹  Hualong Yang¹  Hong Jiang¹  Wei Zhang¹  Jun Yu¹ 

[1] School of Computer Science and Engineering Xi’an Technological University No.2 Xuefu Middle Road

关键词: Generative Adversarial Network;    Capsule Network;    Capsule Generative Adversarial Network;    Capsule Discriminator;    Super-resolution Reconstruction;   

DOI  :  10.2478/ijanmc-2022-0038

学科分类：社会科学、人文和艺术（综合）

来源: Asociación Regional De Diálisis Y Trasplantes Renales

【 摘 要 】

Using each part of the image's spatial information to generate better local details of the image is a key problem that super-resolution reconstruction has been facing. At present, mainstream super-resolution reconstruction networks are all built based on convolutional neural networks (CNN). Some of these methods based on Generative Adversarial Networks (GAN) have good performance in high-frequency details and visual effects. However, because CNN lacks the necessary attention to local spatial information, the reconstruction method is prone to problems such as excessive image brightness and unnatural pixel regions in the image. Therefore, using the capsule network's excellent perception of hierarchical spatial information and local feature relationships, the author proposes a super-resolution reconstruction based on capsule network CSRGAN. The experiment's final result shows that compared with the pure convolution method RDN, the PSNR value of CSRGAN is increased by 0.14, which is closer to the original image.

【 授权许可】

CC BY-NC-ND