BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T171600
DTEND;TZID=Asia/Tokyo:20241204T172800
UID:siggraphasia_SIGGRAPH Asia 2024_sess122_papers_166@linklings.com
SUMMARY:Compositional Neural Textures
DESCRIPTION:Technical Papers\n\nPeihan Tu (University of Maryland, College
  Park); Li-Yi Wei (Adobe Research); and Matthias Zwicker (University of Ma
 ryland, College Park)\n\nTexture plays a vital role in enhancing visual ri
 chness in both real photographs and computer-generated imagery. However, t
 he process of editing textures often involves laborious and repetitive man
 ual adjustments of textons, which are the recurring local patterns that ch
 aracterize textures. This work introduces a fully unsupervised approach fo
 r representing textures using a compositional neural model that captures i
 ndividual textons. We\nrepresent each texton as a 2D Gaussian function who
 se spatial support approximates\nits shape, and an associated feature that
  encodes its detailed appearance. By modeling a texture as a discrete comp
 osition of Gaussian textons, the representation offers both expressiveness
  and ease of editing. Textures can be edited by modifying the compositiona
 l Gaussians within the latent space, and new textures can be efficiently s
 ynthesized by feeding the modified Gaussians through a generator network i
 n a feed-forward manner. This approach enables a wide range of application
 s, including transferring appearance from an image texture to another imag
 e, diversifying textures, texture interpolation, revealing/modifying textu
 re variations, edit propagation, texture animation, and direct texton mani
 pulation. The proposed\napproach contributes to advancing texture analysis
 , modeling, and editing techniques, and opens up new possibilities for cre
 ating visually appealing images with controllable textures.\n\nRegistratio
 n Category: Full Access, Full Access Supporter\n\nLanguage Format: English
  Language\n\nSession Chair: Minhyuk Sung (Korea Advanced Institute of Scie
 nce and Technology (KAIST))
URL:https://asia.siggraph.org/2024/program/?id=papers_166&sess=sess122
END:VEVENT
END:VCALENDAR