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_222@linklings.com
SUMMARY:Efficient Light Probes for Real-time Global Illumination
DESCRIPTION:Technical Communications, Technical Papers\n\nEfficient Light 
 Probes for Real-time Global Illumination\n\nGuo, Zong, Song, Fu, Tao...\n\
 nReproducing physically-based global illumination (GI) effects has been a 
 long-standing demand for many real-time graphical applications. In pursuit
  of this goal, many recent engines resort to some form of light probes bak
 ed in a precomputation stage. Unfortunately, the GI effects stemming from 
 the precomputed probes are rather limited due to the constraints in the pr
 obe storage, representation or query. In this paper, we propose a neural m
 ethod for probe-based GI rendering which can generate a wide range of GI e
 ffects, including glossy reflection with multiple bounces, in complex scen
 es. The key contributions behind our work include a gradient-based search 
 algorithm and a neural image reconstruction method. The search algorithm i
 s designed to reproject the probes' contents to any query viewpoint, witho
 ut introducing parallax errors, and converges fast to the optimal solution
 . The neural image reconstruction method, based on a dedicated neural netw
 ork and several G-buffers, tries to recover high-quality images from low-q
 uality inputs due to limited resolution or (potential) low sampling rate o
 f the probes. This neural method makes the generation of light probes effi
 cient. Moreover, a temporal reprojection strategy and a temporal loss are 
 employed to improve temporal stability for animation sequences. The whole 
 pipeline runs in real-time (>30 frames per second) even for high-resolutio
 n (1920x1080) outputs, thanks to the fast convergence rate of the gradient
 -based search algorithm and a light-weight design of the neural network. E
 xtensive experiments on multiple complex scenes have been conducted to sho
 w the superiority of our method over the state-of-the-arts.\n\nRegistratio
 n Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: 
 IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_222&sess=sess16
 1
END:VEVENT
END:VCALENDAR