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:20260114T163649Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T161500
DTEND;TZID=Australia/Melbourne:20231215T162500
UID:siggraphasia_SIGGRAPH Asia 2023_sess159_papers_406@linklings.com
SUMMARY:Constructive Solid Geometry on Neural Signed Distance Fields
DESCRIPTION:Zoë Marschner (Massachusetts Institute of Technology, Carnegie
  Mellon University); Silvia Sellán (University of Toronto); Hsueh-Ti Dere
 k Liu (Roblox Research); and Alec Jacobson (University of Toronto)\n\nSign
 ed Distance Fields (SDFs) parameterized by neural networks have recently g
 ained popularity as a fundamental geometric representation. However, editi
 ng the shape encoded by a neural SDF remains an open challenge.  A temptin
 g approach is to leverage common geometric operators (e.g., boolean operat
 ions) to edit neural SDFs, but such edits often lead to incorrect non-SDF 
 outputs (which we call Pseudo-SDFs), preventing them from being used for d
 ownstream tasks. In this paper, we characterize the space of Pseudo-SDFs, 
 which are eikonal yet not true distance functions, and derive the closest 
 point loss, a novel regularizer that encourages the output to be an exact 
 SDF. We demonstrate the applicability of our regularization to many operat
 ions in which traditional methods cause a Pseudo-SDF to arise, such as CSG
  and swept volumes, and  produce a true (neural) SDF for the result of the
 se operations.\n\nRegistration Category: Full Access\n\nSession Chair: Fei
  Hou (Institute of Software, Chinese Academy of Sciences; University of Ch
 inese Academy of Sciences)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_406&sess=sess159
END:VEVENT
END:VCALENDAR