DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yun, Kwan | ko |
dc.contributor.author | Seo, Kwanggyoon | ko |
dc.contributor.author | Seo, Chang Wook | ko |
dc.contributor.author | Yoon, Soyeon | ko |
dc.contributor.author | Kim, Seong Cheol | ko |
dc.contributor.author | Ji, Soohyun | ko |
dc.contributor.author | Ashtari, Amirsaman | ko |
dc.contributor.author | Noh, Junyong | ko |
dc.date.accessioned | 2024-08-27T10:00:06Z | - |
dc.date.available | 2024-08-27T10:00:06Z | - |
dc.date.created | 2024-06-18 | - |
dc.date.issued | 2024-05 | - |
dc.identifier.citation | Computer Graphics Forum, v.43, no.2 | - |
dc.identifier.issn | 0167-7055 | - |
dc.identifier.uri | http://hdl.handle.net/10203/322432 | - |
dc.description.abstract | Facial sketches are both a concise way of showing the identity of a person and a means to express artistic intention. While a few techniques have recently emerged that allow sketches to be extracted in different styles, they typically rely on a large amount of data that is difficult to obtain. Here, we propose StyleSketch, a method for extracting high-resolution stylized sketches from a face image. Using the rich semantics of the deep features from a pretrained StyleGAN, we are able to train a sketch generator with 16 pairs of face and the corresponding sketch images. The sketch generator utilizes part-based losses with two-stage learning for fast convergence during training for high-quality sketch extraction. Through a set of comparisons, we show that StyleSketch outperforms existing state-of-the-art sketch extraction methods and few-shot image adaptation methods for the task of extracting high-resolution abstract face sketches. We further demonstrate the versatility of StyleSketch by extending its use to other domains and explore the possibility of semantic editing. The project page can be found in https://kwanyun.github.io/stylesketch_project. | - |
dc.language | English | - |
dc.publisher | John Wiley and Sons Inc | - |
dc.title | Stylized Face Sketch Extraction via Generative Prior with Limited Data | - |
dc.type | Article | - |
dc.identifier.wosid | 001217076200001 | - |
dc.identifier.scopusid | 2-s2.0-85192104964 | - |
dc.type.rims | ART | - |
dc.citation.volume | 43 | - |
dc.citation.issue | 2 | - |
dc.citation.publicationname | Computer Graphics Forum | - |
dc.identifier.doi | 10.1111/cgf.15045 | - |
dc.contributor.localauthor | Noh, Junyong | - |
dc.contributor.nonIdAuthor | Yun, Kwan | - |
dc.contributor.nonIdAuthor | Seo, Kwanggyoon | - |
dc.contributor.nonIdAuthor | Yoon, Soyeon | - |
dc.contributor.nonIdAuthor | Ji, Soohyun | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article; Early Access | - |
dc.subject.keywordAuthor | CCS Concepts | - |
dc.subject.keywordAuthor | center dot Computing methodologies -> | - |
dc.subject.keywordAuthor | Artificial intelligence | - |
dc.subject.keywordAuthor | Computer vision | - |
dc.subject.keywordAuthor | Computer vision | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.