BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035308Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221207T110000
DTEND;TZID=Asia/Seoul:20221207T123000
UID:siggraphasia_SIGGRAPH Asia 2022_sess161_papers_235@linklings.com
SUMMARY:Lightweight Neural Basis Functions for All-Frequency Shading
DESCRIPTION:Technical Communications, Technical Papers\n\nLightweight Neur
 al Basis Functions for All-Frequency Shading\n\nXu, Zeng, Wu, Wang, Yan\n\
 nBasis functions provide both the abilities for compact representation and
  the properties for efficient computation. Therefore, they are pervasively
  used in rendering to perform all-frequency shading. However, common basis
  functions, including spherical harmonics (SH), wavelets, and spherical Ga
 ussians (SG) all have their own limitations, such as low-frequency for SH,
  not rotationally invariant for wavelets, and no multiple product support 
 for SG. In this paper, we present \empf{neural basis functions}, an implic
 it and data-driven set of basis functions that circumvents the limitations
  with all desired properties. We first introduce a representation neural n
 etwork that takes any general 2D spherical function (e.g. environment ligh
 ting, BRDF, and visibility) as input and projects it onto the latent space
  as coefficients of our neural basis functions. Then, we design several li
 ghtweight neural networks that perform different types of computation, giv
 ing our basis functions different computational properties such as double/
 triple product integrals and rotations. We demonstrate the practicality of
  our neural basis functions by integrating them into all-frequency shading
  applications, showing that our method not only achieves a compression rat
 e of $0.39\%$ and $10\times$-$40\times$ better performance than wavelets a
 t equal quality, but also renders all-frequency lighting effects in real-t
 ime without the aforementioned limitations from classic basis functions.\n
 \nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLIS
 H\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_235&sess=sess16
 1
END:VEVENT
END:VCALENDAR