Self-tuned deep super resolution

Zhangyang Wang, Yingzhen Yang, Zhaowen Wang, Shiyu Chang, Wei Han, Jianchao Yang, Thomas Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

44 Scopus citations

Abstract

Deep learning has been successfully applied to image super resolution (SR). In this paper, we propose a deep joint super resolution (DJSR) model to exploit both external and self similarities for SR. A Stacked Denoising Convolutional Auto Encoder (SDCAE) is first pre-trained on external examples with proper data augmentations. It is then fine-tuned with multi-scale self examples from each input, where the reliability of self examples is explicitly taken into account. We also enhance the model performance by sub-model training and selection. The DJSR model is extensively evaluated and compared with state-of-the-arts, and show noticeable performance improvements both quantitatively and perceptually on a wide range of images.

Original languageEnglish (US)
Title of host publication2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
PublisherIEEE Computer Society
Pages1-8
Number of pages8
ISBN (Electronic)9781467367592
DOIs
StatePublished - Oct 19 2015
Externally publishedYes
EventIEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 - Boston, United States
Duration: Jun 7 2015Jun 12 2015

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2015-October
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
CountryUnited States
CityBoston
Period6/7/156/12/15

Keywords

  • Adaptation models
  • Convolutional codes
  • Image resolution
  • Joints
  • Pediatrics
  • Training
  • Yttrium

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Self-tuned deep super resolution'. Together they form a unique fingerprint.

Cite this