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:20240214T070247Z
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:Technical Papers\n\nYael Vinker (Tel Aviv University, Google R
 esearch); Andrey Voynov (Google Research); Daniel Cohen-Or (Tel Aviv Unive
 rsity, Google Research); and Ariel Shamir (Reichman University)\n\nA creat
 ive idea is often born from transforming, combining, and modifying ideas f
 rom existing visual examples capturing various concepts.\nHowever, one can
 not simply copy the concept as a whole, and inspiration is achieved by exa
 mining certain aspects of the concept. Hence, it is often necessary to sep
 arate a concept into different aspects to provide new perspectives.\nIn th
 is paper, we propose a method to decompose a visual concept, represented a
 s a set of images, into different visual aspects encoded in a hierarchical
  tree structure. We utilize large vision-language models and their rich la
 tent space for concept decomposition and generation. \nEach node in the tr
 ee 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 reg
 ularizations to guide the optimization of the embedding vectors encoded in
  the nodes to follow the hierarchical structure of the tree.\nOur method a
 llows to explore and discover new concepts derived from the original one. 
 The tree provides the possibility of endless visual sampling at each node,
  allowing the user to explore the hidden sub-concepts of the object of int
 erest.\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 sen
 tences to apply such aspects to new designs.\n\nRegistration Category: Ful
 l Access\n\nSession Chair: Peng-Shuai Wang (Peking University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_200&sess=sess150
END:VEVENT
END:VCALENDAR