BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171530Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T135800
DTEND;TZID=Asia/Tokyo:20241206T140900
UID:siggraphasia_SIGGRAPH Asia 2024_sess146_papers_240@linklings.com
SUMMARY:A Dynamic By-example BTF Synthesis Scheme
DESCRIPTION:Zilin Xu (University of California Santa Barbara), Zahra Monta
 zeri (University of Manchester), Beibei Wang (Nanjing University), and Lin
 g-Qi Yan (University of California Santa Barbara)\n\nMeasured Bidirectiona
 l Texture Function (BTF) can faithfully reproduce a realistic appearance b
 ut is costly to acquire and store due to its 6D nature (2D spatial and 4D 
 angular). Therefore, it is practical and necessary for rendering to synthe
 size BTFs from a small example patch. While previous methods managed to pr
 oduce plausible results, we find that they seldomly take into consideratio
 n the property of being dynamic, so a BTF must be synthesized before the r
 endering process, resulting in limited size, costly pre-generation and sto
 rage issues. In this paper, we propose a dynamic BTF synthesis scheme, whe
 re a BTF at any position only needs to be synthesized when being queried. 
 Our insight is that, with the recent advances in neural dimension reductio
 n methods, a BTF can be decomposed into disjoint low-dimensional component
 s. We can perform dynamic synthesis only on the positional dimensions, and
  during rendering, recover the BTF by querying and combining these low-dim
 ensional functions with the help of a lightweight Multilayer Perceptron (M
 LP). Consequently, we obtain a fully dynamic 6D BTF synthesis scheme that 
 does not require any pre-generation, which enables efficient rendering of 
 our infinitely large and non-repetitive BTFs on the fly.  We demonstrate t
 he effectiveness of our method through various types of BTFs taken from UB
 O2014.\n\nRegistration Category: Full Access, Full Access Supporter\n\nLan
 guage Format: English Language\n\nSession Chair: Valentin Deschaintre (Ado
 be Research)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_240&sess=sess146
END:VEVENT
END:VCALENDAR