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_463@linklings.com
SUMMARY:MetaLayer: A Meta-learned BSDF Model for Layered Materials
DESCRIPTION:Technical Papers\n\nJie Guo, Zeru Li, and Xueyan He (Nanjing U
 niversity); Beibei Wang (Nankai University, Nanjing University of Science 
 and Technology); Wenbin Li and Yanwen Guo (Nanjing University); and Ling-Q
 i Yan (University of California, Santa Barbara)\n\nReproducing the appeara
 nce of arbitrary layered materials has long been a critical challenge in c
 omputer graphics, with regard to the demanding requirements of both physic
 al accuracy and low computation cost. Recent studies have demonstrated pro
 mising results by learning-based representations that implicitly encode th
 e appearance of complex (layered) materials by neural networks. However, e
 xisting generally-learned models often struggle between strong representat
 ion ability and high runtime performance, and also lack physical/perceptua
 l parameters for material editing. To address these concerns, we introduce
  MetaLayer, a new methodology leveraging meta-learning for modeling and re
 ndering layered materials. MetaLayer contains two networks: a BSDFNet that
  compactly encodes the appearance of layered materials, and a MetaNet that
  establishes the mapping between the physical parameters of each material 
 and the weights of its corresponding implicit neural representation. A new
  positional encoding method and a well-designed training strategy are empl
 oyed to improve the performance and quality of the neural model. As a new 
 learning-based representation, the proposed MetaLayer model provides both 
 fast responses to material editing and high-quality results for a wide ran
 ge of layered materials, outperforming existing layered BSDF models.\n\nRe
 gistration Category: Full Access, Enhanced Access, Trade Exhibitor, Experi
 ence Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_463&sess=sess209
END:VEVENT
END:VCALENDAR