Application of Generative Adversarial Network in Super-Resolution Image Reconstruction

Application of Generative Adversarial Network in Super-Resolution Image Reconstruction

Aiming at the problems of over-fitting of existing convolutional neural network image super-resolution algorithm and insufficient convergence of loss function, combined with super-resolution algorithm and generative adversarial network (GAN) theory, the super-resolution algorithm PESRGAN (permeabili...

Full description

Bibliographic Details
Main Author: WANG Xinyun, LI Dan
Format: Article
Language:zho
Published: Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2020-04-01
Series:Jisuanji kexue yu tansuo
Subjects:
convolutional neural network (cnn)
super-resolution image reconstruction
generative adversarial network (gan)
quadruple sampling
Online Access:http://fcst.ceaj.org/CN/abstract/abstract2171.shtml

Internet

http://fcst.ceaj.org/CN/abstract/abstract2171.shtml

Similar Items