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:20240214T070245Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T171600
DTEND;TZID=Australia/Melbourne:20231213T173100
UID:siggraphasia_SIGGRAPH Asia 2023_sess146_papers_463@linklings.com
SUMMARY:MetaLayer: A Meta-learned BSDF Model for Layered Materials
DESCRIPTION:Technical Communications, Technical Papers\n\nJie Guo, Zeru Li
 , and Xueyan He (Nanjing University); Beibei Wang (Nankai University, Nanj
 ing University of Science and Technology); Wenbin Li and Yanwen Guo (Nanji
 ng University); and Ling-Qi Yan (University of California, Santa Barbara)\
 n\nReproducing the appearance of arbitrary layered materials has long been
  a critical challenge in computer graphics, with regard to the demanding r
 equirements of both physical accuracy and low computation cost. Recent stu
 dies have demonstrated promising results by learning-based representations
  that implicitly encode the appearance of complex (layered) materials by n
 eural networks. However, existing generally-learned models often struggle 
 between strong representation ability and high runtime performance, and al
 so lack physical/perceptual parameters for material editing. To address th
 ese concerns, we introduce MetaLayer, a new methodology leveraging meta-le
 arning for modeling and rendering layered materials. MetaLayer contains tw
 o networks: a BSDFNet that compactly encodes the appearance of layered mat
 erials, and a MetaNet that establishes the mapping between the physical pa
 rameters of each material and the weights of its corresponding implicit ne
 ural representation. A new positional encoding method and a well-designed 
 training strategy are employed to improve the performance and quality of t
 he neural model. As a new learning-based representation, the proposed Meta
 Layer model provides both fast responses to material editing and high-qual
 ity results for a wide range of layered materials, outperforming existing 
 layered BSDF models.\n\nRegistration Category: Full Access\n\nSession Chai
 r: Hongzhi Wu (Zhejiang University; State Key Lab of CAD and CG, Zhejiang 
 University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_463&sess=sess146
END:VEVENT
END:VCALENDAR