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:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_165@linklings.com
SUMMARY:Sprite-from-Sprite: Cartoon Animation Decomposition with Self-supe
 rvised Sprite Estimation
DESCRIPTION:Technical Papers\n\nSprite-from-Sprite: Cartoon Animation Deco
 mposition with Self-supervised Sprite Estimation\n\nZhang, Wong, Liu\n\nWe
  present an approach to decompose cartoon animation videos into a set of `
 `sprites'' --- the basic units of digital cartoons that depict the content
 s and transforms of each animated objects. The sprites in real-world carto
 ons are unique: artists may draw arbitrary sprite animations for expressiv
 eness, where the animated content is often complicated, irregular, and cha
 llenging; alternatively, artists may also reduce their workload by tweenin
 g and adjusting sprites, or even reuse static sprites, in which case the t
 ransformations are relatively regular and simple. Based on these observati
 ons, we propose a sprite decomposition framework using Pixel Multilayer Pe
 rceptrons (Pixel MLPs) where the estimation of each sprite is conditioned 
 on and guided by all other sprites. In this way, once those relatively reg
 ular and simple sprites are resolved, the decomposition of the remaining '
 'challenging'' sprites can simplified and eased with the guidance of other
  sprites. We call this method ``sprite-from-sprite'' cartoon decomposition
 . We study ablative architectures of our framework, and the user study dem
 onstrates that our results are the most preferred ones in 19/20 cases.\n\n
 Registration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACC
 ESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_165&sess=sess15
 3
END:VEVENT
END:VCALENDAR