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:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_390@linklings.com
SUMMARY:Neural James-Stein Combiner for Unbiased and Biased Renderings
DESCRIPTION:Technical Papers\n\nNeural James-Stein Combiner for Unbiased a
 nd Biased Renderings\n\nGu, Iglesias-Guitian, Moon\n\nUnbiased rendering a
 lgorithms such as path tracing produce accurate images given an infinite n
 umber of samples, but in practice, the techniques often leave visually dis
 tracting artifacts (i.e., noise) in their rendered images due to a limited
  time budget. A favored approach for mitigating the noise problem is apply
 ing learning-based denoisers to unbiased but noisy rendered images and sup
 pressing the noise while preserving image details. However, such denoising
  techniques typically introduce a systematic error, i.e., the denoising bi
 as, which does not decline as rapidly when increasing the sample size, unl
 ike the other type of error, i.e., variance. It can technically lead to sl
 ow numerical convergence of the denoising techniques. We propose a new com
 bination framework built upon the James-Stein (JS) estimator, which merges
  a pair of unbiased and biased rendering images, e.g., a path-traced image
  and its denoised result. Unlike existing post-correction techniques for i
 mage denoising, our framework helps an input denoiser have lower errors th
 an its unbiased input without relying on accurate estimation of per-pixel 
 denoising errors. We demonstrate that our framework based on the well-esta
 blished JS theories allows us to improve the error reduction rates of stat
 e-of-the-art learning-based denoisers more robustly than recent post-denoi
 sers.\n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPER
 IENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_390&sess=sess15
 3
END:VEVENT
END:VCALENDAR