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:20260114T163641Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T130000
DTEND;TZID=Australia/Melbourne:20231213T131500
UID:siggraphasia_SIGGRAPH Asia 2023_sess169_papers_220@linklings.com
SUMMARY:Towards Garment Sewing Pattern Reconstruction from a Single Image
DESCRIPTION:Lijuan Liu (Sea AI Lab); Xiangyu Xu (Xi'an Jiaotong University
 , Sea AI Lab); and Zhijie Lin, Jiabin Liang, and Shuicheng Yan (Sea AI Lab
 )\n\nGarment sewing pattern represents the intrinsic rest shape of a garme
 nt, 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 photos for augmenting th
 ese applications. To solve the problem, we first synthesize a versatile da
 taset, named SewFactory, which consists of around 1M images and ground-tru
 th sewing patterns for model training and quantitative evaluation. SewFact
 ory covers a wide range of human poses, body shapes, and sewing patterns, 
 and possesses realistic appearances thanks to the proposed human texture s
 ynthesis network. Then, we propose a two-level Transformer network called 
 Sewformer, which significantly improves the sewing pattern prediction perf
 ormance. Extensive experiments demonstrate that the proposed framework is 
 effective in recovering sewing patterns and well generalizes to casually-t
 aken human photos.\n\nRegistration Category: Full Access\n\nSession Chair:
  Bernd Bickel (ETH Zürich, Google)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_220&sess=sess169
END:VEVENT
END:VCALENDAR