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_247@linklings.com
SUMMARY:Metappearance: Meta-Learning for Visual Appearance Reproduction
DESCRIPTION:Technical Papers\n\nMetappearance: Meta-Learning for Visual Ap
 pearance Reproduction\n\nFischer, Ritschel\n\nThere currently exist two ma
 in approaches to reproducing visual appearance using Machine Learning (ML)
 : The first is training models that generalize over different instances of
  a problem, e.g., different images of a dataset. As one-shot approaches, t
 hese offer fast inference, but often fall short in quality. The second app
 roach does not train models that generalize across tasks, but rather over-
 fit a single instance of a problem, e.g., a flash image of a material. The
 se methods offer high quality, but take long to train. We suggest to combi
 ne both techniques end-to-end using meta-learning: We over-fit onto a sing
 le problem instance in an inner loop, while also learning how to do so eff
 iciently in an outer-loop across many exemplars. To this end, we derive th
 e required formalism that allows applying meta-learning to a wide range of
  visual appearance reproduction problems: textures, Bi-directional Reflect
 ance Distribution Functions (BRDFs), spatially-varying\nBRDFs (svBRDFs), i
 llumination or the entire light transport of a scene. The effects of meta-
 learning parameters on several different aspects of visual appearance are 
 analyzed in our framework, and specific guidance for different tasks is pr
 ovided. Metapperance enables visual quality that is similar to over-fit ap
 proaches in only a fraction of their runtime while keeping the adaptivity 
 of general models.\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_247&sess=sess15
 3
END:VEVENT
END:VCALENDAR