BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163653Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T120000
DTEND;TZID=Australia/Melbourne:20231214T121500
UID:siggraphasia_SIGGRAPH Asia 2023_sess150_papers_200@linklings.com
SUMMARY:Concept Decomposition for Visual Exploration and Inspiration
DESCRIPTION:Yael Vinker (Tel Aviv University, Google Research); Andrey Voy
 nov (Google Research); Daniel Cohen-Or (Tel Aviv University, Google Resear
 ch); and Ariel Shamir (Reichman University)\n\nA creative idea is often bo
 rn from transforming, combining, and modifying ideas from existing visual 
 examples capturing various concepts.\nHowever, one cannot simply copy the 
 concept as a whole, and inspiration is achieved by examining certain aspec
 ts of the concept. Hence, it is often necessary to separate a concept into
  different aspects to provide new perspectives.\nIn this paper, we propose
  a method to decompose a visual concept, represented as a set of images, i
 nto different visual aspects encoded in a hierarchical tree structure. We 
 utilize large vision-language models and their rich latent space for conce
 pt decomposition and generation. \nEach node in the tree represents a sub-
 concept using a learned vector embedding injected into the latent space of
  a pretrained text-to-image model. We use a set of regularizations to guid
 e the optimization of the embedding vectors encoded in the nodes to follow
  the hierarchical structure of the tree.\nOur method allows to explore and
  discover new concepts derived from the original one. The tree provides th
 e possibility of endless visual sampling at each node, allowing the user t
 o explore the hidden sub-concepts of the object of interest.\nThe learned 
 aspects in each node can be combined within and across trees to create new
  visual ideas, and can be used in natural language sentences to apply such
  aspects to new designs.\n\nRegistration Category: Full Access\n\nSession 
 Chair: Peng-Shuai Wang (Peking University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_200&sess=sess150
END:VEVENT
END:VCALENDAR