BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030653Z
LOCATION:Meeting Room S426+S427\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251215T133100
DTEND;TZID=Asia/Hong_Kong:20251215T134200
UID:siggraphasia_SIGGRAPH Asia 2025_sess106_papers_1013@linklings.com
SUMMARY:ReSTIR PG: Path Guiding with Spatiotemporally Resampled Paths
DESCRIPTION:ZHENG ZENG (University of California Santa Barbara, NVIDIA); M
 arkus Kettunen, Chris Wyman, and Lifan Wu (NVIDIA); Ravi Ramamoorthi (NVID
 IA, University of California San Diego); Ling-Qi Yan (Mohamed bin Zayed Un
 iversity of Artificial Intelligence); and Daqi Lin (NVIDIA)\n\nWe present 
 ReSTIR Path Guiding (ReSTIR-PG), a real-time method that extracts guiding 
 distributions from resampled paths produced by ReSTIR and uses them to gen
 erate improved initial candidates for the next frame. While ReSTIR signifi
 cantly reduces variance through spatiotemporal resampling, its effectivene
 ss is ultimately limited by the quality of the initial candidates, which a
 re often poorly distributed and introduce correlation artifacts. Our key o
 bservation is that ReSTIR’s accepted paths already approximate the target 
 path contribution density, and that their bounce directions follow the ide
 al distribution for local path guiding – the product of incident radiance 
 and the cosine-weighted BSDF. We exploit this structure to fit lightweight
  guiding distributions using each frame’s resampled paths by density estim
 ation. Compared to conventional guiding based on raw path-traced samples, 
 ReSTIR-PG closes the loop between guiding and resampling. Our method achie
 ves lower variance, faster response time to scene change, reduced correlat
 ion artifacts, all while preserving real-time performance.\n\nRegistration
  Category: Full Access, Full Access Supporter\n\nSession Chair: Yuchi Huo 
 (Zhejiang University, Korea Advanced Institute of Science and Technology)\
 n\n
END:VEVENT
END:VCALENDAR