BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212946Z
LOCATION:Mile High 1
DTSTART;TZID=America/Denver:20240729T145000
DTEND;TZID=America/Denver:20240729T150000
UID:siggraph_SIGGRAPH 2024_sess108_papers_497@linklings.com
SUMMARY:Blue Noise for Diffusion Models
DESCRIPTION:Xingchang Huang and Corentin Salaun (Max Planck Institute for 
 Informatics); Cristina Vasconcelos (Google DeepMind); Christian Theobalt (
 Max Planck Institute for Informatics); Cengiz Oztireli (Google Research, U
 niversity of Cambridge); and Gurprit Singh (Max Planck Institute for Infor
 matics)\n\nMost existing diffusion models use Gaussian noise for training.
  We introduce a novel class of deterministic diffusion models using time-v
 arying noise (i.e., from white to blue noise) to incorporate correlation w
 ithin images during training. Further, our framework allows introducing co
 rrelation across images within a single mini-batch to improve gradient flo
 w.\n\nInterest Area: Research & Education\n\nRecording: Livestreamed, Reco
 rded\n\nKeyword: AI, Machine Learning, Rendering\n\nRegistration Category:
  Full Conference, Full Conference Supporter, Virtual Access, Exhibitor Ful
 l Conference, Monday\n\nSession Chair: Holly Rushmeier (Yale University)\n
 \n
END:VEVENT
END:VCALENDAR