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_385@linklings.com
SUMMARY:TileGen: Tileable, Controllable Material Generation and Capture
DESCRIPTION:Technical Papers\n\nTileGen: Tileable, Controllable Material G
 eneration and Capture\n\nZhou, Hasan, Deschaintre, Guerrero, Sunkavalli...
 \n\nRecent methods (e.g. MaterialGAN) have used unconditional GANs to gene
 rate per-pixel material maps, or as a prior to reconstruct materials from 
 input photographs. These models can generate varied random material appear
 ance, but do not have any mechanism to constrain the generated material to
  a specific category or to control the coarse structure of the generated m
 aterial, such as the exact brick layout on a brick wall. Furthermore, mate
 rials reconstructed from a single input photo commonly have artifacts and 
 are\ngenerally not tileable, which limits their use in practical content c
 reation pipelines. We propose TileGen, a generative model for SVBRDFs that
  is specific to a material category, always tileable, and optionally condi
 tional on a provided input structure pattern. TileGen is a variant of Styl
 eGAN whose architecture is modified to always produce tileable (periodic) 
 material maps. In addition to the standard “style” latent code, TileGen ca
 n optionally take a condition image, giving a user direct control over the
  dominant spatial (and optionally color) features of the material. For exa
 mple, in brick materials, the user can specify a brick layout and the bric
 k color, or in leather materials, the locations of wrinkles and folds. Our
  inverse rendering approach can find a material perceptually matching a si
 ngle target photograph by optimization. This reconstruction can also be co
 nditional on a user-provided pattern. The resulting materials are tileable
 , can be larger than the target image, and are editable by varying the con
 dition.\n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXP
 ERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_385&sess=sess15
 3
END:VEVENT
END:VCALENDAR