BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260805T205600Z
LOCATION:Room 408 A
DTSTART;TZID=America/Los_Angeles:20260720T144000
DTEND;TZID=America/Los_Angeles:20260720T145000
UID:siggraph_SIGGRAPH 2026_sess137_papers_395@linklings.com
SUMMARY:A LoD of Gaussians: Out-of-Core Training and Rendering for Seamles
 s Ultra-Large Scene Reconstruction
DESCRIPTION:Felix Windisch, Thomas Köhler, Lukas Radl, Mattia D'urso, and 
 Michael Steiner (Graz University of Technology); Dieter Schmalstieg (Unive
 rsity of Stuttgart, Graz University of Technology); and Markus Steinberger
  (Graz University of Technology)\n\nGaussian Splatting struggles with larg
 e scenes due to memory limits and chunking artifacts. We introduce "A LoD 
 of Gaussians," a new framework enabling ultra-large scene training and ren
 dering on a single consumer GPU. Through out-of-core streaming and Level-o
 f-Detail, it achieves seamless multi-scale reconstruction without relying 
 on scene partitioning.\n\nInterest Area: Research & Education\n\nKeyword: 
 Artificial Intelligence/Machine Learning, Geometry, Modeling, Real-Time, R
 endering\n\nRegistration Category: Full Conference Supporter, Full Confere
 nce\n\nSession Chair: Young Min Kim (Seoul National University)\n\n
END:VEVENT
END:VCALENDAR