Image super-resolution reconstruction based on improved Dirac residual network

• Published in: Multidimensional systems and signal processing Vol. 32; no. 4; pp. 1065 - 1082
• Main Authors: Yang, Xin, Xie, Tangxin, Liu, Li, Zhou, Dake
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2021; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Artificial neural networks; Circuits and Systems; Electrical Engineering; Engineering; Image reconstruction; Image resolution; Mapping; Signal,Image and Speech Processing; Training; Visual effects; Deep learning; Super-resolution; Dirac residual network; Convolutional neural network

In recent years, to improve the nonlinear feature mapping ability of the image super-resolution network, the depth of the convolutional neural network is getting deeper and deeper. In the existing residual network, the the residual block’s output and input are added directly through the skip connect...