Face Super Resolution for VLQ facial images via parent patch matching

Liang Chen, Ruimin Hu, Zhen Han, Zhongyuan Wang, Qing Li, Zheng Lu

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

Abstract

Face Super Resolution(FSR) is to infer High Resolution(HR) facial images from given Low Resolution(LR) ones with the assistance of LR and HR training pairs. Among existing methods, local patch based methods are superior in visual and objective quality than global based methods. These local patch based methods are based on the consistency assumption that the neighbors in HR/LR space form similar local geometry. But when LR images are Very Low Quality(VLQ), the LR space is seriously contaminated that even two distinct patches look similar, which means that the consistency assumption is not well held anymore. To this end, in this paper we use the target patch as well as the surrounding pixels, which we called parent patch, to represent the target patch. By incorporating the peripheral information, the parent patch is much more robust to noise in the LR and HR consistency learning. The effectiveness of proposed method is verified both quantitatively and qualitatively.

Original languageEnglish
Title of host publication2016 International Joint Conference on Neural Networks, IJCNN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2515-2521
Number of pages7
ISBN (Electronic)9781509006199
DOIs
Publication statusPublished - 31 Oct 2016
Externally publishedYes
Event2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada
Duration: 24 Jul 201629 Jul 2016

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2016-October

Conference

Conference2016 International Joint Conference on Neural Networks, IJCNN 2016
Country/TerritoryCanada
CityVancouver
Period24/07/1629/07/16

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint

Dive into the research topics of 'Face Super Resolution for VLQ facial images via parent patch matching'. Together they form a unique fingerprint.

Cite this