BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030655Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T171300
DTEND;TZID=Asia/Hong_Kong:20251216T172400
UID:siggraphasia_SIGGRAPH Asia 2025_sess129_papers_2019@linklings.com
SUMMARY:Neural Image abstraction using long smoothing B-splines
DESCRIPTION:Daniel Berio (Goldsmiths, University of London); Michael Stroh
  (University of Konstanz); Sylvain Calinon (Idiap Research Institute); Fre
 deric Fol Leymarie (Goldsmiths, University of London); Oliver Deussen (Uni
 versity of Konstanz); and Ariel Shamir (Reichman University)\n\nWe integra
 te smoothing B-splines into a standard differentiable vector graphics (Dif
 fVG) pipeline through linear mapping, and show how this can be used to gen
 erate smooth and arbitrarily long paths within image-based deep learning s
 ystems. We take advantage of derivative-based smoothing costs for parametr
 ic control of  fidelity vs. simplicity tradeoffs, while also enabling styl
 ization control in geometric and image spaces. The proposed pipeline is co
 mpatible with recent vector graphics generation and vectorization methods.
 \nWe demonstrate the versatility of our approach with four applications ai
 med at the generation of stylized vector graphics: stylized space-filling 
 path generation, stroke-based image abstraction, closed-area image abstrac
 tion, and stylized text generation.\n\nRegistration Category: Full Access,
  Full Access Supporter\n\nSession Chair: Zeyu Wang (The Hong Kong Universi
 ty of Science and Technology (Guangzhou), The Hong Kong University of Scie
 nce and Technology)\n\n
END:VEVENT
END:VCALENDAR