BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212944Z
LOCATION:Mile High 4
DTSTART;TZID=America/Denver:20240729T141000
DTEND;TZID=America/Denver:20240729T142000
UID:siggraph_SIGGRAPH 2024_sess106_paperstog_108@linklings.com
SUMMARY:Importance Sampling BRDF Derivatives
DESCRIPTION:Yash Belhe and Bing Xu (University of California San Diego), S
 ai Praveen Bangaru (Massachusetts Institute of Technology (MIT)), Ravi Ram
 amoorthi and Tzu-Mao Li (University of California San Diego), and Yash Bel
 he\n\nWe propose the first set of techniques to efficiently importance sam
 ple the derivatives of several popular analytical BRDF models (e.g. anisot
 ropic GGX/ Beckmann/ Ashikhmin-Shirley, Hanrahan-Kreuger, Oren-Nayar etc.)
 . Our estimators are practical and provide significant variance improvemen
 t in all settings from direct illumination to global illumination effects 
 like caustics.\n\nInterest Area: Research & Education\n\nRecording: Livest
 reamed, Recorded\n\nKeyword: Machine Learning, Rendering\n\nRegistration C
 ategory: Full Conference, Full Conference Supporter, Virtual Access, Exhib
 itor Full Conference, Monday\n\nSession Chair: Ioannis Gkioulekas (Carnegi
 e Mellon University)\n\n
END:VEVENT
END:VCALENDAR