BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035309Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221207T170000
DTEND;TZID=Asia/Seoul:20221207T183000
UID:siggraphasia_SIGGRAPH Asia 2022_sess179_papers_433@linklings.com
SUMMARY:Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace R
 epresentation
DESCRIPTION:Technical Communications, Technical Papers, TOG\n\nImplicit Co
 nversion of Manifold B-Rep Solids by Neural Halfspace Representation\n\nGu
 o, Liu, Pan, Guo\n\nWe present a novel implicit representation --- neural 
 halfspace representation (NH-Rep), to convert manifold B-Rep solids to imp
 licit representations. NH-Rep is a Boolean tree built on a set of implicit
  functions represented by the neural network, and the composite Boolean fu
 nction is capable of representing solid geometry while preserving sharp fe
 atures. We propose an efficient algorithm to extract the Boolean tree from
  a manifold B-Rep solid and devise a neural network-based optimization app
 roach to compute the implicit functions.\nWe demonstrate the high quality 
 offered by our conversion algorithm on ten thousand manifold B-Rep CAD mod
 els that contain various curved patches including NURBS, and the superiori
 ty of our learning approach over other representative implicit conversion 
 algorithms in terms of surface reconstruction, sharp feature preservation,
  signed distance field approximation, and robustness to various surface ge
 ometry, as well as a set of applications supported by NH-Rep.\n\nRegistrat
 ion Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat
 : IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_433&sess=sess17
 9
END:VEVENT
END:VCALENDAR