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:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T153000
DTEND;TZID=Asia/Seoul:20221206T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess157_papers_165@linklings.com
SUMMARY:Sprite-from-Sprite: Cartoon Animation Decomposition with Self-supe
 rvised Sprite Estimation
DESCRIPTION:Technical Communications, Technical Papers\n\nSprite-from-Spri
 te: Cartoon Animation Decomposition with Self-supervised Sprite Estimation
 \n\nZhang, Wong, Liu\n\nWe present an approach to decompose cartoon animat
 ion videos into a set of ``sprites'' --- the basic units of digital cartoo
 ns that depict the contents and transforms of each animated objects. The s
 prites in real-world cartoons are unique: artists may draw arbitrary sprit
 e animations for expressiveness, where the animated content is often compl
 icated, irregular, and challenging; alternatively, artists may also reduce
  their workload by tweening and adjusting sprites, or even reuse static sp
 rites, in which case the transformations are relatively regular and simple
 . Based on these observations, we propose a sprite decomposition framework
  using Pixel Multilayer Perceptrons (Pixel MLPs) where the estimation of e
 ach sprite is conditioned on and guided by all other sprites. In this way,
  once those relatively regular and simple sprites are resolved, the decomp
 osition of the remaining ''challenging'' sprites can simplified and eased 
 with the guidance of other sprites. We call this method ``sprite-from-spri
 te'' cartoon decomposition. We study ablative architectures of our framewo
 rk, and the user study demonstrates that our results are the most preferre
 d ones in 19/20 cases.\n\nRegistration Category: FULL ACCESS, ON-DEMAND AC
 CESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_165&sess=sess15
 7
END:VEVENT
END:VCALENDAR