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:20240214T070250Z
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:Technical Papers\n\nZoë Marschner (Massachusetts Institute of 
 Technology, Carnegie Mellon University); Silvia Sellán (University of Tor
 onto); Hsueh-Ti Derek Liu (Roblox Research); and Alec Jacobson (University
  of Toronto)\n\nSigned Distance Fields (SDFs) parameterized by neural netw
 orks have recently gained popularity as a fundamental geometric representa
 tion. However, editing the shape encoded by a neural SDF remains an open c
 hallenge.  A tempting approach is to leverage common geometric operators (
 e.g., boolean operations) to edit neural SDFs, but such edits often lead t
 o incorrect non-SDF outputs (which we call Pseudo-SDFs), preventing them f
 rom being used for downstream tasks. In this paper, we characterize the sp
 ace of Pseudo-SDFs, which are eikonal yet not true distance functions, and
  derive the closest point loss, a novel regularizer that encourages the ou
 tput to be an exact SDF. We demonstrate the applicability of our regulariz
 ation to many operations in which traditional methods cause a Pseudo-SDF t
 o arise, such as CSG and swept volumes, and  produce a true (neural) SDF f
 or the result of these operations.\n\nRegistration Category: Full Access\n
 \nSession Chair: Fei Hou (Institute of Software, Chinese Academy of Scienc
 es; University of Chinese Academy of Sciences)
URL:https://asia.siggraph.org/2023/full-program?id=papers_406&sess=sess159
END:VEVENT
END:VCALENDAR