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:20231214T114000
DTEND;TZID=Australia/Melbourne:20231214T115000
UID:siggraphasia_SIGGRAPH Asia 2023_sess150_papers_216@linklings.com
SUMMARY:CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration
DESCRIPTION:Technical Papers\n\nJingyu Hu, Ka-Hei Hui, and Zhengzhe Liu (T
 he Chinese University of Hong Kong); Hao (Richard) Zhang (Simon Fraser Uni
 versity); and Chi-Wing Fu (The Chinese University of Hong Kong)\n\nThis pa
 per presents CLIPXPlore, a new framework that leverages a vision-language 
 model to guide the exploration of the 3D shape space. Many recent methods 
 have been developed to encode 3D shapes into a learned latent shape space 
 to enable generative design and modeling. Yet, existing methods lack effec
 tive exploration mechanisms, despite the rich information. To this end, we
  propose to leverage CLIP, a powerful pre-trained vision-language model, t
 o aid the shape space exploration. Our idea is threefold. First, we couple
  the CLIP and shape spaces by generating paired CLIP and shape codes throu
 gh sketch images and training a mapper network to connect the two spaces. 
 Second, to explore the space around a given shape, we formulate\na co-opti
 mization strategy to search for the CLIP code that better matches the geom
 etry of the shape. Third, we design three exploration scenarios, binary-at
 tribute-guided, text-guided, and sketch-guided, to locate suitable explora
 tion trajectories in shape space and induce meaningful changes to the shap
 e. We perform a series of experiments to quantitatively and visually\ncomp
 are CLIPXPlore with different baselines in each of the three scenarios, sh
 owing that CLIPXPlore can produce many meaningful exploration results that
  cannot be achieved by the existing solutions.\n\nRegistration Category: F
 ull Access\n\nSession Chair: Peng-Shuai Wang (Peking University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_216&sess=sess150
END:VEVENT
END:VCALENDAR