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:20240214T070241Z
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_231@linklings.com
SUMMARY:EMS: 3D Eyebrow Modeling from Single-view Images
DESCRIPTION:Technical Papers\n\nChenghong Li, Leyang Jin, and Yujian Zheng
  (The Chinese University of Hong Kong, Shenzhen); Yizhou Yu (The Universit
 y of Hong Kong); and Xiaoguang Han (The Chinese University of Hong Kong, S
 henzhen)\n\nEyebrows play a critical role in facial expression and appeara
 nce. Although the 3D digitization of faces is well explored, less attentio
 n has been drawn to 3D eyebrow modeling. In this work, we propose EMS, the
  first learning-based framework for single-view 3D eyebrow reconstruction.
  Following the methods of scalp hair reconstruction, we also represent the
  eyebrow as a set of fiber curves and convert the reconstruction to fibers
  growing problem. Three modules are then carefully designed: RootFinder fi
 rstly localizes the fiber root positions which indicates where to grow; Or
 iPredictor predicts an orientation filed in the 3D space to guide the grow
 ing of fibers; FiberEnder is designed to determine when to stop the growth
  of each fiber. Our OriPredictor is directly borrowing the method used in 
 hair reconstruction. Considering the differences between hair and eyebrows
 , both RootFinder and FiberEnder are newly proposed. Specifically, to cope
  with the challenge that the root location is severely occluded, we formul
 ate root localization as a density map estimation task. Given the predicte
 d density map, a density-based clustering method is further used for findi
 ng the roots. For each fiber, the growth starts from the root point and mo
 ves step by step until the ending, where each step is defined as an orient
 ed line with a constant length according to the predicted orientation fiel
 d. To determine when to end, a pixel-aligned RNN architecture is designed 
 to form a binary classifier, which outputs stop or not for each growing st
 ep. To support the training of all proposed networks, we build the first 3
 D synthetic eyebrow dataset that contains 400 high-quality eyebrow models 
 manually created by artists. Extensive experiments have demonstrated the e
 ffectiveness of the proposed EMS pipeline on a variety of different eyebro
 w styles and lengths, ranging from short and sparse to long bushy eyebrows
 .\n\nRegistration Category: Full Access, Enhanced Access, Trade Exhibitor,
  Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_231&sess=sess209
END:VEVENT
END:VCALENDAR