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:20260114T163651Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T090000
DTEND;TZID=Australia/Melbourne:20231215T091500
UID:siggraphasia_SIGGRAPH Asia 2023_sess155_papers_439@linklings.com
SUMMARY:Manifold Path Guiding for Importance Sampling Specular Chains
DESCRIPTION:Zhimin Fan (Nanjing University); Pengpei Hong (University of U
 tah); Jie Guo (Nanjing University); Changqing Zou (Zhejiang Lab; State Key
  Lab of CAD&CG, Zhejiang University); Yanwen Guo (Nanjing University); and
  Ling-Qi Yan (University of California, Santa Barbara)\n\nComplex visual e
 ffects such as caustics are often produced by light paths containing multi
 ple consecutive specular vertices (dubbed specular chains), which pose a c
 hallenge to unbiased estimation in Monte Carlo rendering.\nIn this work, w
 e study the light transport behavior within a sub-path that is comprised o
 f a specular chain and two non-specular separators. \nWe show that the spe
 cular manifolds formed by all the sub-paths could be exploited to provide 
 coherence among sub-paths. By reconstructing continuous energy distributio
 ns from historical and coherent sub-paths, seed chains can be generated in
  the context of importance sampling and converge to admissible chains thro
 ugh manifold walks. We verify that importance sampling the seed chain in t
 he continuous space reaches the goal of importance sampling the discrete a
 dmissible specular chain. \nBased on these observations and theoretical an
 alyses, a progressive pipeline, manifold path guiding, is designed and imp
 lemented to importance sample challenging paths featuring long specular ch
 ains. To our best knowledge, this is the first general framework for impor
 tance sampling discrete specular chains in regular Monte Carlo rendering. 
 Extensive experiments demonstrate that our method outperforms state-of-the
 -art unbiased solutions with up to 40× variance reduction, especially in t
 ypical scenes containing long specular chains and complex visibility.\n\nR
 egistration Category: Full Access\n\nSession Chair: Sing Chun Lee (Bucknel
 l University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_439&sess=sess155
END:VEVENT
END:VCALENDAR