BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_520@linklings.com
SUMMARY:Deep Adaptive Sampling and Reconstruction using Analytic Distribut
 ions
DESCRIPTION:Technical Papers\n\nDeep Adaptive Sampling and Reconstruction 
 using Analytic Distributions\n\nSalehi, Manzi, Roethlin, Schroers, Weber..
 .\n\nWe propose an adaptive sampling and reconstruction method for offline
  Monte Carlo rendering. Our method produces sampling maps constrained by a
  user-defined budget that minimize the expected future denoising error. Co
 mpared to other state-of-the-art methods, which produce the necessary trai
 ning data on the fly by composing pre-rendered images, our method samples 
 from analytic noise distributions instead. These distributions are compact
  and closely approximate the pixel value distributions stemming from Monte
  Carlo rendering. Our method can efficiently sample training data by lever
 aging only a few per-pixel statistics of the target distribution, which pr
 ovides several benefits over the current state of the art. Most notably, o
 ur analytic distributions’ modeling accuracy and sampling efficiency incre
 ase with sample count, essential for high-quality offline rendering. Altho
 ugh our distributions are approximate, our method supports joint end-to-en
 d training of the sampling and denoising networks. Finally, we propose the
  addition of a global summary module to our architecture that accumulates 
 valuable information from image regions outside of the network’s receptive
  field. This information discourages sub-optimal decisions based on local 
 information. Our evaluation against other state-of-the-art neural sampling
  methods demonstrates denoising quality and data efficiency improvements.\
 n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE 
 ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_520&sess=sess15
 3
END:VEVENT
END:VCALENDAR