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:20231214T123000
DTEND;TZID=Australia/Melbourne:20231214T124000
UID:siggraphasia_SIGGRAPH Asia 2023_sess150_papers_720@linklings.com
SUMMARY:ReparamCAD: Zero-shot CAD Re-Parameterization for Interactive Mani
 pulation
DESCRIPTION:Technical Papers\n\nMilin Kodnongbua and Benjamin Jones (Unive
 rsity of Washington), Maaz Bin Safeer Ahmad and Vladimir Kim (Adobe), and 
 Adriana Schulz (University of Washington)\n\nParametric CAD models encode 
 entire families of shapes that should, in principle, be easy for designers
  to explore, but are in practice difficult to manipulate due to implicit s
 emantic constraints between parameter values. Finding and enforcing these 
 semantic constraints purely from geometry or programmatic shape representa
 tions is not possible because these constraints are ultimately a form of d
 esign intent, and are informed by the designer's experience and semantic i
 n the real world. While individual pieces of geometry cannot encode this c
 ontextual knowledge, is it encoded in large foundation models. We use larg
 e language and image models to understand what the meaningful space of var
 iation is for a shape, and synthesize a new parametric CAD program that ca
 ptures these variations, allowing for easy design space exploration along 
 meaningful design axes.\n\nRegistration Category: Full Access\n\nSession C
 hair: Peng-Shuai Wang (Peking University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_720&sess=sess150
END:VEVENT
END:VCALENDAR