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:20230103T035312Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221209T103000
DTEND;TZID=Asia/Seoul:20221209T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess173_papers_250@linklings.com
SUMMARY:Marginal Multiple Importance Sampling
DESCRIPTION:Technical Communications, Technical Papers\n\nMarginal Multipl
 e Importance Sampling\n\nWest, Georgiev, Hachisuka\n\nMultiple importance 
 sampling (MIS) is a powerful tool to combine different sampling techniques
  in a provably good manner. MIS requires that the techniques' probability 
 density functions (PDFs) are readily evaluable point-wise. However, this r
 equirement may not be satisfied when (some of) those PDFs are marginals, i
 .e., integrals of other PDFs. We generalize MIS to combine samples from su
 ch marginal PDFs. The key idea is to consider each marginalization domain 
 as a continuous space of sampling techniques with readily evaluable (condi
 tional) PDFs. We stochastically select techniques from these spaces and co
 mbine the samples drawn from them into an unbiased estimator. Prior work h
 as dealt with the special cases of multiple classical techniques or a sing
 le marginal one. Our formulation can handle mixtures of those.\n\nWe apply
  our marginal MIS formulation to light-transport simulation to demonstrate
  its utility. We devise a marginal path sampling framework that makes prev
 iously intractable sampling techniques practical and significantly broaden
 s the path-sampling choices beyond what is presently possible. We highligh
 t results from two algorithms based on marginal MIS: a novel formulation o
 f path-space filtering at multiple vertices along a camera path and a simi
 lar filtering method for photon-density estimation.\n\nRegistration Catego
 ry: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSO
 N, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_250&sess=sess17
 3
END:VEVENT
END:VCALENDAR