Paper Info
Title
Single Image Super-Resolution with a Parameter Economic Residual-Like Convolutional Neural Network.
Abstract
Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large amount of parameters or computational cost as CNN goes deeper. Correspondingly, the skip connections or identity mapping shortcuts are utilized to avoid gradient exploding/vanishing problem. To tackle with the second problem, a parameter economic CNN architecture which has carefully designed width, depth and skip connections was proposed. Experimental results have demonstrated that the proposed CNN model can not only achieve state-of-theart PSNR and SSIM results for single image super-resolution but also produce visually pleasant results.
Year
DOI
Venue
2017
10.1007/978-3-319-51811-4_29
Lecture Notes in Computer Science
Keywords
Field
DocType
Super-resolution,Deep residual-like convolutional neural network,Skip connections,The mount of parameters
Computer vision,Residual,Architecture,Vision problem,Pattern recognition,Convolutional neural network,Computer science,Time delay neural network,Artificial intelligence,Deep learning,Superresolution
Conference
Volume
ISSN
Citations 
10132
0302-9743
4
PageRank 
References 
Authors
0.41
16
4
Name
Order
Citations
PageRank
Ze Yang140.41
Kai Zhang268626.59
Yudong Liang3402.02
Jinjun Wang429115.86