BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035312Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221209T140000
DTEND;TZID=Asia/Seoul:20221209T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess178_papers_306@linklings.com
SUMMARY:Neural Brushstroke Engine: Learning a Latent Style Space of Intera
 ctive Drawing Tools
DESCRIPTION:Technical Communications, Technical Papers\n\nNeural Brushstro
 ke Engine: Learning a Latent Style Space of Interactive Drawing Tools\n\nS
 hugrina, Li, Fidler\n\nWe propose Neural Brushstroke Engine, the first met
 hod to apply deep generative models\nto learn a distribution of interactiv
 e drawing tools. \nOur conditional GAN model learns the latent \nspace of 
 drawing styles from a small set (about 200) of unlabeled images in differe
 nt media.\nOnce trained, a single model can texturize stroke patches drawn
  by the artist,\nemulating a diverse collection of brush styles in the la
 tent space. In order to\nenable interactive painting on a canvas of arbit
 rary size, we design a painting engine able to support real-time seamless 
 patch-based generation,\nwhile allowing artists direct control of stroke 
 shape, color and thickness.\nWe show that the latent space learned by our
  model generalizes to unseen drawing and more experimental styles (e.g. be
 ads) by embedding real styles into the latent space. We explore other appl
 ications of the continuous latent space, such as optimizing brushes to ena
 ble painting in the style of an existing artwork, automatic line drawing s
 tylization, brush interpolation, and even natural language search over a c
 ontinuous space of drawing tools. Our prototype received positive feedback
  from a small group of digital artists.\n\nRegistration Category: FULL ACC
 ESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_306&sess=sess17
 8
END:VEVENT
END:VCALENDAR