Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/81662
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Electronic and Information Engineering-
dc.creatorLiu, ZS-
dc.creatorSiu, WC-
dc.creatorChan, YL-
dc.date.accessioned2020-02-10T12:28:29Z-
dc.date.available2020-02-10T12:28:29Z-
dc.identifier.issn2169-3536en_US
dc.identifier.urihttp://hdl.handle.net/10397/81662-
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.rightsThis work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0en_US
dc.rightsThe following publication Z. Liu, W. Siu and Y. Chan, "Reference Based Face Super-Resolution," in IEEE Access, vol. 7, pp. 129112-129126, 2019 is available at https://dx.doi.org/10.1109/ACCESS.2019.2934078en_US
dc.subjectFace super-resolutionen_US
dc.subjectDeep feature extractionen_US
dc.subjectStyle transferen_US
dc.titleReference based face super-resolutionen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage129112en_US
dc.identifier.epage129126en_US
dc.identifier.volume7en_US
dc.identifier.doi10.1109/ACCESS.2019.2934078en_US
dcterms.abstractDespite the great progress of image super-resolution in recent years, face super-resolution has still much room to explore good visual quality while preserving original facial attributes for larger up-scaling factors. This paper investigates a new research direction in face super-resolution, called Reference based face Super-Resolution (RefSR), in which a reference facial image containing genuine attributes is provided in addition to the low-resolution images for super-resolution. We focus on transferring the key information extracted from reference facial images to the super-resolution process to guarantee the content similarity between the reference and super-resolution image. We propose a novel Conditional Variational AutoEncoder model for this Reference based Face Super-Resolution (RefSR-VAE). By using the encoder to map the reference image to the joint latent space, we can then use the decoder to sample the encoder results to super-resolve low-resolution facial images to generate super-resolution images with good visual quality. We create a benchmark dataset on reference based face super-resolution (RefSR-Face) for general research use, which contains reference images paired with low-resolution images of various pose, emotions, ages and appearance. Both objective and subjective evaluations were conducted, which demonstrate the great potential of using reference images for face super-resolution. By comparing it with state-of-the-art super-resolution approaches, our proposed approach also achieves superior performance.-
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitationIEEE access, 2019, v. 7, p. 129112-129126en_US
dcterms.isPartOfIEEE accessen_US
dcterms.issued2019-
dc.identifier.isiWOS:000487233800078-
dc.identifier.scopus2-s2.0-85077975142-
dc.description.validate202002 bcrc-
dc.description.oaVersion of Recorden_US
dc.identifier.FolderNumberOA_Scopus/WOSen_US
dc.description.pubStatusPublisheden_US
Appears in Collections:Journal/Magazine Article
Files in This Item:
File Description SizeFormat 
Liu_Reference_Face_Super-Resolution.pdf3.22 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

Page views

49
Citations as of Jun 26, 2022

Downloads

227
Citations as of Jun 26, 2022

SCOPUSTM   
Citations

7
Citations as of Jun 30, 2022

WEB OF SCIENCETM
Citations

4
Citations as of Jun 30, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.