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:20260817T171532Z
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:Kirill Brodt and Mikhail Bessmeltsev (University of Montreal)\
 n\nOne of the primary reasons for the high cost of traditional animation i
 s the inbetweening process, where artists manually draw each intermediate 
 frame necessary for smooth motion. Making this process more efficient has 
 been at the core of computer graphics research for years, yet the industry
  has adopted very few solutions. Most existing solutions either require ve
 ctor input or resort to tight inbetweening; often, they attempt to fully a
 utomate the process. In industry, however, keyframes are often spaced far 
 apart, drawn in raster format, and contain occlusions. Moreover, inbetween
 ing is fundamentally an artistic process, so the artist should maintain hi
 gh-level control over it.\n\nWe address these issues by proposing a novel 
 inbetweening system for bitmap character drawings. In our setup, the artis
 t can control motion by animating a 3D skeleton between the keyframe poses
 . Our system then performs skeleton-based deformation of the bitmap drawin
 gs into the same pose and employs deep learning to blend the deformed imag
 es.\n\nHowever, deforming drawings with occlusions is complex, as it requi
 res a piecewise smooth deformation field. To address this, we observe that
  this deformation field is smooth when the drawing is lifted into 3D. Our 
 system therefore optimizes topology of a 2.5D partially layered template t
 hat we use to get the final piecewise-smooth deformaton, effectively resol
 ving occlusions.\n\nWe validate our system through a series of animations,
  qualitative and quantitative comparisons, and user studies, demonstrating
  that our approach consistently outperforms the state of the art and our r
 esults are consistent with the viewers' perception.\n\nRegistration Catego
 ry: Full Access, Full Access Supporter\n\nLanguage Format: English Languag
 e\n\nSession Chair: Changjian Li (University of Edinburgh)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_692&sess=sess135
END:VEVENT
END:VCALENDAR