Face super-resolution based on multi-source references

Rui Wang, Muwei Jian, Paul Smith, Hui Yu

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

13 Downloads (Pure)

Abstract

This paper proposes a multi-source references (MSR) based face super-resolution (FSR) model. More specifically, to enhance the low-quality large-scale reconstruction of faces without the involvement of face prior knowledge, we propose a multi-source references based FSR framework exploiting a constructed reference library of nonidentity faces and an information mining module for external and internal references. Experimental results show that the proposed model can provide more satisfactory and reliable face super-resolution results than the-state-of-the-art methods.
Original languageEnglish
Title of host publication2022 15th International Conference on Human System Interaction (HSI)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781665468220
ISBN (Print)9781665468237
DOIs
Publication statusPublished - 30 Aug 2022
Event2022 15th International Conference on Human System Interaction (HSI) - Melbourne, Australia
Duration: 28 Jul 202231 Jul 2022
https://hsi2022.welcometohsi.org/

Publication series

Name2022 15th International Conference on Human System Interaction (HSI)
PublisherIEEE
ISSN (Print)2158-2246
ISSN (Electronic)2158-2254

Conference

Conference2022 15th International Conference on Human System Interaction (HSI)
Country/TerritoryAustralia
CityMelbourne
Period28/07/2231/07/22
Internet address

Keywords

  • multi-source
  • face super-resolution
  • prior knowledge

Fingerprint

Dive into the research topics of 'Face super-resolution based on multi-source references'. Together they form a unique fingerprint.

Cite this