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:20260114T163632Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_778@linklings.com
SUMMARY:Zero-Shot 3D Shape Correspondence
DESCRIPTION:Ahmed Abdelreheem and Abdelrahman Eldesokey (King Abdullah Uni
 versity of Science and Technology (KAUST)), Maks Ovsjanikov (Centre Nation
 al de la Recherche Scientifique - Laboratoire d'informatique de l'École Po
 lytechnique (LIX)), and Peter Wonka (King Abdullah University of Science a
 nd Technology (KAUST))\n\nWe propose a novel zero-shot approach to computi
 ng correspondences\nbetween 3D shapes. Existing approaches mainly focus on
  isometric and\nnear-isometric shape pairs (e.g., human vs. human), but le
 ss attention has\nbeen given to strongly non-isometric and inter-class sha
 pe matching (e.g., human vs. cow). To this end, we introduce a fully autom
 atic method that exploits the exceptional reasoning capabilities of recent
  foundation models in language and vision to tackle difficult shape corres
 pondence problems. Our approach comprises multiple stages. First, we class
 ify the 3D shapes in a zero-shot manner by feeding rendered shape views to
  a language-vision model (e.g., BLIP2) to generate a list of class proposa
 ls per shape. These proposals are unified into a single class per shape by
  employing the reasoning capabilities of ChatGPT. Second, we attempt to se
 gment the two shapes in a zero-shot manner, but in contrast to the co-segm
 entation problem, we do not require a mutual set of semantic regions. Inst
 ead, we propose to exploit the in-context learning capabilities of ChatGPT
  to generate two different sets of semantic regions for each shape and a s
 emantic mapping between them. This enables our approach to match strongly 
 non-isometric shapes with significant differences in geometric structure. 
 Finally, we employ the generated semantic mapping to produce coarse corres
 pondences that can further be refined by the functional maps framework to 
 produce dense point-to-point maps. Our approach, despite its simplicity, p
 roduces highly plausible results in a zero-shot manner, especially between
  strongly non-isometric shapes.\n\nRegistration Category: Full Access, Enh
 anced Access, Trade Exhibitor, Experience Hall Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_778&sess=sess209
END:VEVENT
END:VCALENDAR