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 C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T114000
DTEND;TZID=Australia/Melbourne:20231214T115000
UID:siggraphasia_SIGGRAPH Asia 2023_sess131_papers_797@linklings.com
SUMMARY:Animating Street View
DESCRIPTION:Mengyi Shan, Brian Curless, Ira Kemelmacher-Shlizerman, and St
 eve Seitz (University of Washington)\n\nWe present a system that automatic
 ally brings street view imagery to life by populating it with naturally be
 having, animated pedestrians and vehicles. Our approach is to remove exist
 ing people and vehicles from the input image, insert moving objects with p
 roper scale, angle, motion and appearance, plan paths and traffic behavior
 , as well as render the scene with plausible occlusion and shadowing effec
 ts. The system achieves these by reconstructing the still image street sce
 ne, simulating crowd behavior, and rendering with consistent lighting, vis
 ibility, occlusions, and shadows. We demonstrate results on a diverse rang
 e of street scenes including regular still images and panoramas.\n\nRegist
 ration Category: Full Access\n\nSession Chair: Neil A. Dodgson (Victoria U
 niversity of Wellington)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_797&sess=sess131
END:VEVENT
END:VCALENDAR