Automatic Vector Caricature via Face Parametrization

Simple item page
dc.contributor.authorMadono, Kokien_US
dc.contributor.authorHold-Geoffroy, Yannicken_US
dc.contributor.authorLi, Yijunen_US
dc.contributor.authorIto, Daichien_US
dc.contributor.authorEchevarria, Joseen_US
dc.contributor.authorSmith, Cameronen_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorDeng, Zhigangen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2023-10-09T07:42:49Z
dc.date.available2023-10-09T07:42:49Z
dc.date.issued2023
dc.description.abstractAutomatic caricature generation is a challenging task that aims to emphasize the subject's facial characteristics while preserving its identity. Due to the complexity of the task, caricatures could exclusively be performed by a trained artist. Recent developments in deep learning have achieved promising results in capturing artistic styles. Despite the success, current methods still struggle to accurately capture the whimsical aspect of caricatures while preserving identity. In this work, we propose Parametric Caricature, the first parametric-based caricature generation that yields vectorized and animatable caricatures. We devise several hundred parameters to encode facial traits, which our method directly predicts instead of estimating the raster caricature like previous methods. To guide the attention of the method, we segment the different parts of the face and retrieve the most similar parts from an artist-made database of caricatures. Our method proposes visually appealing caricatures more adapted to use as avatars than existing methods, as demonstrated by our user study.en_US
dc.description.sectionheadersImages, Vectorization, and Layouts
dc.description.seriesinformationPacific Graphics Short Papers and Posters
dc.identifier.doi10.2312/pg.20231271
dc.identifier.isbn978-3-03868-234-9
dc.identifier.pages57-64
dc.identifier.pages8 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20231271
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/pg20231271
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Artistic Image Generation; Image Rendering -> Image Vectorization
dc.subjectComputing methodologies
dc.subjectArtistic Image Generation
dc.subjectImage Rendering
dc.subjectImage Vectorization
dc.titleAutomatic Vector Caricature via Face Parametrizationen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
057-064.pdf
Size:
23.82 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
pgshort_supp.pdf
Size:
53.85 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1230_mm.mp4
Size:
45.84 MB
Format:
Unknown data format
Download
Collections
PG2023 Short Papers and Posters