Learning Implicit Glyph Shape Representation

Automatic generation of fonts can greatly facilitate the font design process, and provide prototypes where designers can draw inspiration from. Existing generation methods are mainly built upon rasterized glyph images to utilize the successful convolutional architecture, but ignore the vector nature...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on visualization and computer graphics. - 1996. - 29(2023), 10 vom: 16. Okt., Seite 4172-4182
Auteur principal: Liu, Ying-Tian (Auteur)
Autres auteurs: Guo, Yuan-Chen, Li, Yi-Xiao, Wang, Chen, Zhang, Song-Hai
Format: Article en ligne
Langue:English
Publié: 2023
Accès à la collection:IEEE transactions on visualization and computer graphics
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM342304747
003 DE-627
005 20250303113746.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2022.3183400  |2 doi 
028 5 2 |a pubmed25n1140.xml 
035 |a (DE-627)NLM342304747 
035 |a (NLM)35709112 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Liu, Ying-Tian  |e verfasserin  |4 aut 
245 1 0 |a Learning Implicit Glyph Shape Representation 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 04.09.2023 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Automatic generation of fonts can greatly facilitate the font design process, and provide prototypes where designers can draw inspiration from. Existing generation methods are mainly built upon rasterized glyph images to utilize the successful convolutional architecture, but ignore the vector nature of glyph shapes. We present an implicit representation, modeling each glyph as shape primitives enclosed by several quadratic curves. This structured implicit representation is shown to be better suited for glyph modeling, and enables rendering glyph images at arbitrary high resolutions. Our representation gives high-quality glyph reconstruction and interpolation results, and performs well on the challenging one-shot font style transfer task comparing to other alternatives both qualitatively and quantitatively 
650 4 |a Journal Article 
700 1 |a Guo, Yuan-Chen  |e verfasserin  |4 aut 
700 1 |a Li, Yi-Xiao  |e verfasserin  |4 aut 
700 1 |a Wang, Chen  |e verfasserin  |4 aut 
700 1 |a Zhang, Song-Hai  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 29(2023), 10 vom: 16. Okt., Seite 4172-4182  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnas 
773 1 8 |g volume:29  |g year:2023  |g number:10  |g day:16  |g month:10  |g pages:4172-4182 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2022.3183400  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 29  |j 2023  |e 10  |b 16  |c 10  |h 4172-4182