模式识别与人工智能
Monday, Apr. 7, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2019, Vol. 32 Issue (3): 259-267    DOI: 10.16451/j.cnki.issn1003-6059.201903007
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Building Deep Neural Networks with Dilated Convolutions to Reconstruct High-Resolution Image
ZHANG Zhuolin1, ZHAO Jianwei1, CAO Feilong1
1.Department of Applied Mathematics, College of Sciences, China Jiliang University, Hangzhou 310018

Download: PDF (1416 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  To expand the perception field with the filter parameters unchanged, dilated convolution is introduced into very deep convolutional networks super-resolution model. Firstly, the perception field of the dilated convolution block with different expansion coefficients is analyzed and a better combination structure is selected as the dilated convolution block. Then, the deep convolution network is constructed by stacking convolution blocks and adding residual connection. Experiment shows that the reconstruction effect can be improved by the constructed network for the larger scaling factors of Set5 dataset. Besides, there are obvious visual advantages.
Key wordsSuper Resolution Reconstruction      Convolutional Neural Network      Dilated Convolution      Residual Connection     
Received: 12 November 2018     
ZTFLH: TN 911.71  
  TP 183  
Fund:Supported by National Natural Science Foundation of China(No.61672477), Natural Science Foundation of Zhejiang Province(No.LY18F020018)
Corresponding Authors: CAO Feilong, Ph.D., professor. His research interests include deep learning and image processing.   
About author:: (ZHANG Zhuolin, master student. His research interests include deep learning and image processing.)
(ZHAO Jianwei, Ph.D., professor. Her research interests include deep learning and image processing.)
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHANG Zhuolin
ZHAO Jianwei
CAO Feilong
Cite this article:   
ZHANG Zhuolin,ZHAO Jianwei,CAO Feilong. Building Deep Neural Networks with Dilated Convolutions to Reconstruct High-Resolution Image[J]. , 2019, 32(3): 259-267.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201903007      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I3/259
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn