BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212943Z
LOCATION:Mile High 2A
DTSTART;TZID=America/Denver:20240729T145000
DTEND;TZID=America/Denver:20240729T150000
UID:siggraph_SIGGRAPH 2024_sess110_papers_476@linklings.com
SUMMARY:NeurCADRecon: Neural Representation for Reconstructing CAD Surface
 s by Enforcing Zero Gaussian Curvature
DESCRIPTION:Qiujie Dong and Rui Xu (Shandong University); Pengfei Wang (Un
 iversity of Hong Kong); Shuangmin Chen (Qingdao University of Science and 
 Technology); Shiqing Xin (Shandong University); Xiaohong Jia (AMSS, Chines
 e Academy of Sciences); Wenping Wang (Texas A&M University); and Changhe T
 u (Shandong University)\n\nIn this paper, we present a self-supervised neu
 ral representation aimed at reconstructing CAD models from low-quality, un
 oriented point clouds. Our approach stands out from traditional reconstruc
 tion methods by applying a zero Gaussian curvature constraint, which empha
 sizes the characteristic of being almost developable and enhances the pres
 ervation of feature points/lines.\n\nInterest Area: Research & Education\n
 \nRecording: Livestreamed, Recorded\n\nKeyword: Geometry, Modeling\n\nRegi
 stration Category: Full Conference, Full Conference Supporter, Virtual Acc
 ess, Exhibitor Full Conference, Monday\n\nSession Chair: Kari Pulli (Googl
 e)\n\n
END:VEVENT
END:VCALENDAR