BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T153100
DTEND;TZID=Asia/Tokyo:20241205T154300
UID:siggraphasia_SIGGRAPH Asia 2024_sess134_papers_860@linklings.com
SUMMARY:VidPanos: Generative Panoramic Videos from Casual Panning Videos
DESCRIPTION:Technical Papers\n\nJingwei Ma (University of Washington); Eri
 ka Lu, Roni Paiss, and Shiran Zada (Google Deepmind); Aleksander Holynski 
 (University of California Berkeley, Google Deepmind); Tali Dekel (Weizmann
  Institute of Science, Google Deepmind); Brian Curless (University of Wash
 ington, Google Deepmind); and Michael Rubinstein and Forrester Cole (Googl
 e Deepmind)\n\nStitching frames of a panning video into a panoramic photog
 raph is a well-understood problem for stationary scenes. When objects are 
 moving, however, a still panorama is not enough to capture the scene. \nWe
  present a method for synthesizing a panoramic video from a casually-captu
 red panning video, as if the original video were captured with a wide-angl
 e camera. We pose panorama synthesis as a space-time outpainting problem, 
 where we aim to create a full panoramic video of the same length as the in
 put video. Consistent completion of the space-time volume requires a power
 ful, realistic prior over video content and motion, for which we adapt gen
 erative video models. Existing generative models do not, however, immediat
 ely extend to panorama completion, as we show. We instead apply video gene
 ration as a component of our panorama synthesis system, and demonstrate ho
 w to exploit the strengths of the models while minimizing their limitation
 s. Our system can create video panoramas for a range of in-the-wild scenes
  including people, vehicles, and flowing water, as well as stationary back
 ground features.\n\nRegistration Category: Full Access, Full Access Suppor
 ter\n\nLanguage Format: English Language\n\nSession Chair: Nanxuan Zhao (A
 dobe Research)
URL:https://asia.siggraph.org/2024/program/?id=papers_860&sess=sess134
END:VEVENT
END:VCALENDAR