BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T133400
DTEND;TZID=Asia/Tokyo:20241205T134600
UID:siggraphasia_SIGGRAPH Asia 2024_sess131_papers_195@linklings.com
SUMMARY:Neural Product Importance Sampling via Warp Composition
DESCRIPTION:Technical Papers\n\nJoey Litalien (McGill University) and Milo
 š Hašan, Fujun Luan, Krishna Mullia, and Iliyan Georgiev (Adobe Research)\
 n\nAchieving high efficiency in modern photorealistic rendering methods hi
 nges on using Monte Carlo sampling distributions that closely approximate 
 the illumination integral estimated for every pixel. Samples are typically
  generated from a set of simple distributions, each targeting a different 
 factor in the integrand, which are combined via multiple importance sampli
 ng. The resulting mixture distribution can be far from the actual product 
 of all factors, leading to sub-optimal variance even for direct-illuminati
 on estimation. We present a learning-based method to efficiently importanc
 e sample illumination product integrals (e.g., the product of environment 
 lighting and material terms) using normalizing flows. Our neural product s
 ampler composes a flow head warp with an emitter tail warp. The small cond
 itional head is represented by a neural spline flow, while the large uncon
 ditional tail is discretized per environment map and its evaluation is ins
 tant. If the conditioning is low-dimensional, the head warp can be discret
 ized for even better performance. We demonstrate variance reduction over p
 rior methods on a range of applications comprising complex geometry, mater
 ials and illumination.\n\nRegistration Category: Full Access, Full Access 
 Supporter\n\nLanguage Format: English Language\n\nSession Chair: Seungyong
  Lee (POSTECH)
URL:https://asia.siggraph.org/2024/program/?id=papers_195&sess=sess131
END:VEVENT
END:VCALENDAR