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:20230103T035312Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221208T170000
DTEND;TZID=Asia/Seoul:20221208T183000
UID:siggraphasia_SIGGRAPH Asia 2022_sess167_papers_385@linklings.com
SUMMARY:TileGen: Tileable, Controllable Material Generation and Capture
DESCRIPTION:Technical Communications, Technical Papers\n\nTileGen: Tileabl
 e, Controllable Material Generation and Capture\n\nZhou, Hasan, Deschaintr
 e, Guerrero, Sunkavalli...\n\nRecent methods (e.g. MaterialGAN) have used 
 unconditional GANs to generate per-pixel material maps, or as a prior to r
 econstruct materials from input photographs. These models can generate var
 ied random material appearance, but do not have any mechanism to constrain
  the generated material to a specific category or to control the coarse st
 ructure of the generated material, such as the exact brick layout on a bri
 ck wall. Furthermore, materials reconstructed from a single input photo co
 mmonly have artifacts and are\ngenerally not tileable, which limits their 
 use in practical content creation pipelines. We propose TileGen, a generat
 ive model for SVBRDFs that is specific to a material category, always tile
 able, and optionally conditional on a provided input structure pattern. Ti
 leGen is a variant of StyleGAN whose architecture is modified to always pr
 oduce tileable (periodic) material maps. In addition to the standard “styl
 e” latent code, TileGen can optionally take a condition image, giving a us
 er direct control over the dominant spatial (and optionally color) feature
 s of the material. For example, in brick materials, the user can specify a
  brick layout and the brick color, or in leather materials, the locations 
 of wrinkles and folds. Our inverse rendering approach can find a material 
 perceptually matching a single target photograph by optimization. This rec
 onstruction can also be conditional on a user-provided pattern. The result
 ing materials are tileable, can be larger than the target image, and are e
 ditable by varying the condition.\n\nRegistration Category: FULL ACCESS, O
 N-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_385&sess=sess16
 7
END:VEVENT
END:VCALENDAR