Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Yeji | - |
dc.contributor.author | Sohn, Kwanghoon | - |
dc.contributor.author | Kim, Ig-Jae | - |
dc.date.accessioned | 2024-03-07T06:30:14Z | - |
dc.date.available | 2024-03-07T06:30:14Z | - |
dc.date.created | 2024-03-07 | - |
dc.date.issued | 2023-10 | - |
dc.identifier.uri | https://pubs.kist.re.kr/handle/201004/149419 | - |
dc.description.abstract | Face 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.language | English | - |
dc.publisher | IEEE | - |
dc.title | Face Photo-Sketch Synthesis Via Domain-Invariant Feature Embedding | - |
dc.type | Conference | - |
dc.identifier.doi | 10.1109/ICIP49359.2023.10222343 | - |
dc.description.journalClass | 1 | - |
dc.identifier.bibliographicCitation | 30th IEEE International Conference on Image Processing (ICIP), pp.66 - 70 | - |
dc.citation.title | 30th IEEE International Conference on Image Processing (ICIP) | - |
dc.citation.startPage | 66 | - |
dc.citation.endPage | 70 | - |
dc.citation.conferencePlace | US | - |
dc.citation.conferencePlace | Kuala Lumpur, MALAYSIA | - |
dc.citation.conferenceDate | 2023-10-08 | - |
dc.relation.isPartOf | 2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | - |
dc.identifier.wosid | 001106821000013 | - |
dc.identifier.scopusid | 2-s2.0-85180745571 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.