BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T145600
DTEND;TZID=Asia/Tokyo:20241205T150800
UID:siggraphasia_SIGGRAPH Asia 2024_sess135_papers_692@linklings.com
SUMMARY:Skeleton-Driven Inbetweening of Bitmap Character Drawings
DESCRIPTION:Technical Papers\n\nKirill Brodt and Mikhail Bessmeltsev (Univ
 ersity of Montreal)\n\nOne of the primary reasons for the high cost of tra
 ditional animation is the inbetweening process, where artists manually dra
 w each intermediate frame necessary for smooth motion. Making this process
  more efficient has been at the core of computer graphics research for yea
 rs, yet the industry has adopted very few solutions. Most existing solutio
 ns either require vector input or resort to tight inbetweening; often, the
 y attempt to fully automate the process. In industry, however, keyframes a
 re often spaced far apart, drawn in raster format, and contain occlusions.
  Moreover, inbetweening is fundamentally an artistic process, so the artis
 t should maintain high-level control over it.\n\nWe address these issues b
 y proposing a novel inbetweening system for bitmap character drawings. In 
 our setup, the artist can control motion by animating a 3D skeleton betwee
 n the keyframe poses. Our system then performs skeleton-based deformation 
 of the bitmap drawings into the same pose and employs deep learning to ble
 nd the deformed images.\n\nHowever, deforming drawings with occlusions is 
 complex, as it requires a piecewise smooth deformation field. To address t
 his, we observe that this deformation field is smooth when the drawing is 
 lifted into 3D. Our system therefore optimizes topology of a 2.5D partiall
 y layered template that we use to get the final piecewise-smooth deformato
 n, effectively resolving occlusions.\n\nWe validate our system through a s
 eries of animations, qualitative and quantitative comparisons, and user st
 udies, demonstrating that our approach consistently outperforms the state 
 of the art and our results are consistent with the viewers' perception.\n\
 nRegistration Category: Full Access, Full Access Supporter\n\nLanguage For
 mat: English Language\n\nSession Chair: Changjian Li (University of Edinbu
 rgh)
URL:https://asia.siggraph.org/2024/program/?id=papers_692&sess=sess135
END:VEVENT
END:VCALENDAR