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:20260114T163645Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T133300
DTEND;TZID=Australia/Melbourne:20231215T134800
UID:siggraphasia_SIGGRAPH Asia 2023_sess137_papers_231@linklings.com
SUMMARY:EMS: 3D Eyebrow Modeling from Single-view Images
DESCRIPTION:Chenghong Li, Leyang Jin, and Yujian Zheng (The Chinese Univer
 sity of Hong Kong, Shenzhen); Yizhou Yu (The University of Hong Kong); and
  Xiaoguang Han (The Chinese University of Hong Kong, Shenzhen)\n\nEyebrows
  play a critical role in facial expression and appearance. Although the 3D
  digitization of faces is well explored, less attention has been drawn to 
 3D eyebrow modeling. In this work, we propose EMS, the first learning-base
 d framework for single-view 3D eyebrow reconstruction. Following the metho
 ds of scalp hair reconstruction, we also represent the eyebrow as a set of
  fiber curves and convert the reconstruction to fibers growing problem. Th
 ree modules are then carefully designed: RootFinder firstly localizes the 
 fiber root positions which indicates where to grow; OriPredictor predicts 
 an orientation filed in the 3D space to guide the growing of fibers; Fiber
 Ender 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 an
 d FiberEnder are newly proposed. Specifically, to cope with the challenge 
 that the root location is severely occluded, we formulate root localizatio
 n as a density map estimation task. Given the predicted density map, a den
 sity-based clustering method is further used for finding the roots. For ea
 ch fiber, the growth starts from the root point and moves step by step unt
 il the ending, where each step is defined as an oriented line with a const
 ant length according to the predicted orientation field. To determine when
  to end, a pixel-aligned RNN architecture is designed to form a binary cla
 ssifier, which outputs stop or not for each growing step. To support the t
 raining of all proposed networks, we build the first 3D synthetic eyebrow 
 dataset that contains 400 high-quality eyebrow models manually created by 
 artists. Extensive experiments have demonstrated the effectiveness of the 
 proposed EMS pipeline on a variety of different eyebrow styles and lengths
 , ranging from short and sparse to long bushy eyebrows.\n\nRegistration Ca
 tegory: Full Access\n\nSession Chair: Weidan Xiong (Shenzhen University, C
 ollege of Computer Science and Software Engineering)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_231&sess=sess137
END:VEVENT
END:VCALENDAR