BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030655Z
LOCATION:Meeting Room S421\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251218T135400
DTEND;TZID=Asia/Hong_Kong:20251218T140500
UID:siggraphasia_SIGGRAPH Asia 2025_sess154_tog_109@linklings.com
SUMMARY:NESI: Neural Explicit-Shape-Intersection-Based Geometry Representa
 tion
DESCRIPTION:Congyi Zhang, Jinfan Yang, Eric Hedlin, and Suzuran Takikawa (
 UBC); Nicholas Vining (NVIDIA, University of British Columbia); Kwang Moo 
 Yi (UBC); Wenping Wang (Texas A&M University); and Alla Sheffer (UBC)\n\nW
 e introduce NESIs, a compact representation of detailed 3D shapes as inter
 sections of neural explicit height-field surfaces (HFs). NESI provides mor
 e accurate approximations of the input than state-of-the-art alternatives 
 with the same parameter count, while efficiently supporting processing ope
 rations such as occupancy queries and parametric access.\n\nRegistration C
 ategory: Full Access, Full Access Supporter\n\nSession Chair: Qingnan Zhou
  (Adobe)\n\n
END:VEVENT
END:VCALENDAR