Full metadata record

DC Field Value Language
dc.contributor.authorChoi, Yeji-
dc.contributor.authorSohn, Kwanghoon-
dc.contributor.authorKim, Ig-Jae-
dc.date.accessioned2024-03-07T06:30:14Z-
dc.date.available2024-03-07T06:30:14Z-
dc.date.created2024-03-07-
dc.date.issued2023-10-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/149419-
dc.description.abstractFace photo-sketch synthesis involves transforming photos into sketches and vice versa. A well-transformed image should preserve its original identity characteristics and naturalness. However, identity preservation remains a challenge because of the large discrepancy between the photo and sketch domains. To this end, we propose a novel face photo-sketch synthesis framework that uses domain-invariant feature embedding (DIFE). The DIFE framework generates images assuming the domain-invariant feature of an image pair for the same person to be the identity information. A joint feature embedding module considers latent features from two different domains as input and transfers them into the domain-invariant latent space. Subsequently, a semantic-aware decoder completes the desired image guided by multiscale facial parsing masks. Experimental results demonstrate that the DIFE method outperforms state-of-the-art approaches visually and perceptually.-
dc.languageEnglish-
dc.publisherIEEE-
dc.titleFace Photo-Sketch Synthesis Via Domain-Invariant Feature Embedding-
dc.typeConference-
dc.identifier.doi10.1109/ICIP49359.2023.10222343-
dc.description.journalClass1-
dc.identifier.bibliographicCitation30th IEEE International Conference on Image Processing (ICIP), pp.66 - 70-
dc.citation.title30th IEEE International Conference on Image Processing (ICIP)-
dc.citation.startPage66-
dc.citation.endPage70-
dc.citation.conferencePlaceUS-
dc.citation.conferencePlaceKuala Lumpur, MALAYSIA-
dc.citation.conferenceDate2023-10-08-
dc.relation.isPartOf2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP-
dc.identifier.wosid001106821000013-
dc.identifier.scopusid2-s2.0-85180745571-
Appears in Collections:
KIST Conference Paper > 2023
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

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

BROWSE