BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190157Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250814T142000
DTEND;TZID=America/Los_Angeles:20250814T143000
UID:siggraph_SIGGRAPH 2025_sess123_papers_665@linklings.com
SUMMARY:Neural BRDF Importance Sampling by Reparameterization
DESCRIPTION:Liwen Wu (University of California San Diego); Sai Bi (Adobe R
 esearch); Zexiang Xu (Hillbot); Hao Tan, Kai Zhang, and Fujun Luan (Adobe 
 Research); Haolin Lu (Max Planck Institute for Informatics); and Ravi Rama
 moorthi (University of California San Diego)\n\nWe introduce a reparameter
 ization-based formulation of neural BRDF importance sampling. Comparing to
  previous methods that construct a probability transform to the BRDF throu
 gh multi-step invertible neural networks, our BRDF sampling is in single s
 tep without needing network invertibility, achieving higher inference spee
 d with the best variance reduction.\n\nInterest Area: Research & Education
 \n\nRecording: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nR
 egistration Category: Full Conference, Virtual Access, Thursday\n\nSession
  Chair: Thomas Leimkühler (MPI Informatik)\n\n
END:VEVENT
END:VCALENDAR