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:20240214T070242Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_220@linklings.com
SUMMARY:Towards Garment Sewing Pattern Reconstruction from a Single Image
DESCRIPTION:Technical Papers\n\nLijuan Liu (Sea AI Lab); Xiangyu Xu (Xi'an
  Jiaotong University, Sea AI Lab); and Zhijie Lin, Jiabin Liang, and Shuic
 heng Yan (Sea AI Lab)\n\nGarment sewing pattern represents the intrinsic r
 est shape of a garment, and is the core for many applications like fashion
  design, virtual try-on, and digital avatars. In this work, we explore the
  challenging problem of recovering garment sewing patterns from daily phot
 os for augmenting these applications. To solve the problem, we first synth
 esize a versatile dataset, named SewFactory, which consists of around 1M i
 mages and ground-truth sewing patterns for model training and quantitative
  evaluation. SewFactory covers a wide range of human poses, body shapes, a
 nd sewing patterns, and possesses realistic appearances thanks to the prop
 osed human texture synthesis network. Then, we propose a two-level Transfo
 rmer network called Sewformer, which significantly improves the sewing pat
 tern prediction performance. Extensive experiments demonstrate that the pr
 oposed framework is effective in recovering sewing patterns and well gener
 alizes to casually-taken human photos.\n\nRegistration Category: Full Acce
 ss, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_220&sess=sess209
END:VEVENT
END:VCALENDAR