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:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_433@linklings.com
SUMMARY:Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace R
 epresentation
DESCRIPTION:Technical Papers\n\nImplicit Conversion of Manifold B-Rep Soli
 ds by Neural Halfspace Representation\n\nGuo, Liu, Pan, Guo\n\nWe present 
 a novel implicit representation --- neural halfspace representation (NH-Re
 p), to convert manifold B-Rep solids to implicit representations. NH-Rep i
 s a Boolean tree built on a set of implicit functions represented by the n
 eural network, and the composite Boolean function is capable of representi
 ng solid geometry while preserving sharp features. We propose an efficient
  algorithm to extract the Boolean tree from a manifold B-Rep solid and dev
 ise a neural network-based optimization approach to compute the implicit f
 unctions.\nWe demonstrate the high quality offered by our conversion algor
 ithm on ten thousand manifold B-Rep CAD models that contain various curved
  patches including NURBS, and the superiority of our learning approach ove
 r other representative implicit conversion algorithms in terms of surface 
 reconstruction, sharp feature preservation, signed distance field approxim
 ation, and robustness to various surface geometry, as well as a set of app
 lications supported by NH-Rep.\n\nRegistration Category: FULL ACCESS, EXPE
 RIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLIS
 H\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_433&sess=sess15
 3
END:VEVENT
END:VCALENDAR