BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163652Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T131500
DTEND;TZID=Australia/Melbourne:20231215T133000
UID:siggraphasia_SIGGRAPH Asia 2023_sess157_papers_378@linklings.com
SUMMARY:Learning based 2D Irregular Shape Packing
DESCRIPTION:Zeshi Yang and Zherong Pan (Tencent America), Manyi Li (Shando
 ng University), and Kui Wu and Xifeng Gao (Tencent America)\n\n2D irregula
 r shape packing is a necessary step to arrange UV patches of a 3D model wi
 thin a texture atlas for memory-efficient appearance rendering in computer
  graphics. Being a joint, combinatorial decision-making problem involving 
 all patch positions and orientations, this problem has well-known NP-hard 
 complexity. Prior solutions either assume a heuristic packing order or mod
 ify the upstream mesh cut and UV mapping to simplify the problem, which ei
 ther limits the packing ratio or incurs robustness or generality issues. I
 nstead, we introduce a learning-assisted 2D irregular shape packing method
  that achieves a high packing quality with minimal requirements from the i
 nput. Our method iteratively selects and groups subsets of UV patches into
  near-rectangular super patches, essentially reducing the problem to bin-p
 acking, based on which a joint optimization is employed to further improve
  the packing ratio. In order to efficiently deal with large problem instan
 ces with hundreds of patches, we train deep neural policies to predict nea
 rly rectangular patch subsets and determine their relative poses, leading 
 to linear time scaling with the number of patches. We demonstrate the effe
 ctiveness of our method on 3 datasets for UV packing, where our method ach
 ieves higher packing ratio over several widely used baselines with competi
 tive computational speed.\n\nRegistration Category: Full Access\n\nSession
  Chair: Chi Wing Fu (The Chinese University of Hong Kong)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_378&sess=sess157
END:VEVENT
END:VCALENDAR