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:20241205T131100
DTEND;TZID=Asia/Tokyo:20241205T132300
UID:siggraphasia_SIGGRAPH Asia 2024_sess131_papers_1039@linklings.com
SUMMARY:BSDF importance sampling using a diffusion model
DESCRIPTION:Technical Papers\n\nZiyang Fu, Yash Belhe, Haolin Lu, Liwen Wu
 , Bing Xu, and Tzu-Mao Li (University of California San Diego)\n\nMany rea
 l-world materials feature complex BSDFs (Bidirectional Scattering Distribu
 tion Functions) that require significant storage, making the use of neural
  networks to represent BSDFs appealing. Previous neural sampling methods, 
 primarily using analytical lobe mixtures and normalizing flows, often stru
 ggle with specular materials, particularly at grazing angles. Furthermore,
  they are limited to reflection, and do not handle transmission. Our key o
 bservation is that previous normalizing flows impose significant restricti
 on in their network architecture for easy computation of the Jacobian. How
 ever, for low-dimensional sampling such as BSDF sampling, the Jacobian com
 putation is not the bottleneck. Therefore, we propose to use diffusion mod
 els to importance sample full BSDFs. Our method has two variants, one for 
 most reflective materials that learns a distribution on a disk, and the ot
 her for extreme specular reflective materials and full BSDFs, which learns
  a distribution on a sphere. Our equal-time evaluations show that our meth
 od outperforms normalizing flows and significantly surpasses them in certa
 in specular materials. Additionally, our model provides an expressive and 
 stable neural sampling method for any complex BSDFs.\n\nRegistration Categ
 ory: Full Access, Full Access Supporter\n\nLanguage Format: English Langua
 ge\n\nSession Chair: Seungyong Lee (POSTECH)
URL:https://asia.siggraph.org/2024/program/?id=papers_1039&sess=sess131
END:VEVENT
END:VCALENDAR