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:20231215T151500
DTEND;TZID=Australia/Melbourne:20231215T152500
UID:siggraphasia_SIGGRAPH Asia 2023_sess138_papers_433@linklings.com
SUMMARY:UVDoc: Neural Grid-based Document Unwarping
DESCRIPTION:Floor Verhoeven, Tanguy Magne, and Olga Sorkine-Hornung (ETH Z
 urich)\n\nRestoring the original, flat appearance of a printed document fr
 om casual photographs of bent and wrinkled pages is a common everyday prob
 lem. In this paper we propose a novel method for grid-based single-image d
 ocument unwarping. Our method performs geometric distortion correction via
  a fully convolutional deep neural network that learns to predict the 3D g
 rid mesh of the document and the corresponding 2D unwarping grid in a mult
 i-task fashion, implicitly encoding the coupling between the shape of a 3D
  piece of paper and its 2D image. In order to allow unwarping models to tr
 ain on data that is more realistic in appearance than the commonly used sy
 nthetic Doc3D dataset we create and publish our own dataset, called UVDoc,
  which combines pseudo-photorealistic document images with physically accu
 rate 3D shape and unwarping function annotations. Our dataset is labeled w
 ith all the information necessary to train our unwarping network, without 
 having to engineer separate loss functions that can deal with the lack of 
 ground-truth typically found in document in the wild datasets. We perform 
 an in-depth evaluation that demonstrates that with the inclusion of our no
 vel pseudo-photorealistic dataset, our relatively small network architectu
 re achieves state-of-the-art results on the DocUNet benchmark. We show tha
 t the pseudo-photorealistic nature of our UVDoc dataset allows for new and
  better evaluation methods, such as lighting-corrected MS-SSIM. We provide
  a novel benchmark dataset that facilitates such evaluations, and propose 
 a metric that quantifies line straightness after unwarping. Our code, resu
 lts and UVDoc dataset will be made publicly available upon publication.\n\
 nRegistration Category: Full Access\n\nSession Chair: Seung-Hwan Baek (POS
 TECH)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_433&sess=sess138
END:VEVENT
END:VCALENDAR