Texture-centralized deep convolutional neural network for single image super resolution

  • Chengqi Li
  • , Zhigang Ren
  • , Bo Yang
  • , Xingyu Wan
  • , Jinjun Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

There have been significant progresses in single image super-resolution (SR) using deep convolutional neural network. In this paper, we propose a modified deep convolutional neural network model incorporated with image texture priors for single image SR. The model consist of a particular feature extraction layer followed by image reconstruction process, aiming to centralize on the image texture information so as to make the overall SR task more effective. This proposal is compared with current state-of-The-Art methods on standard images. Our experimental results confirmed that, incorporating image texture prior information with conventional high-resolution image reconstruction process can lead to better performance and faster convergence speed simultaneously.

Original languageEnglish
Title of host publicationProceedings - 2017 Chinese Automation Congress, CAC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3707-3710
Number of pages4
ISBN (Electronic)9781538635247
DOIs
StatePublished - 29 Dec 2017
Event2017 Chinese Automation Congress, CAC 2017 - Jinan, China
Duration: 20 Oct 201722 Oct 2017

Publication series

NameProceedings - 2017 Chinese Automation Congress, CAC 2017
Volume2017-January

Conference

Conference2017 Chinese Automation Congress, CAC 2017
Country/TerritoryChina
CityJinan
Period20/10/1722/10/17

Keywords

  • Super-resolution
  • deep convolutional neural network
  • image texture prior

Fingerprint

Dive into the research topics of 'Texture-centralized deep convolutional neural network for single image super resolution'. Together they form a unique fingerprint.

Cite this