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:20260417T190158Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250812T145000
DTEND;TZID=America/Los_Angeles:20250812T150000
UID:siggraph_SIGGRAPH 2025_sess103_papers_364@linklings.com
SUMMARY:CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image
DESCRIPTION:Kaixin Yao, Longwen Zhang, Xinhao Yan, Yan Zeng, and Qixuan Zh
 ang (ShanghaiTech University, Deemos); Jiayuan Gu (ShanghaiTech University
 ); Wei Yang (Huazhong University of Science and Technology); and Lan Xu an
 d Jingyi Yu (ShanghaiTech University)\n\nWe introduce CAST, an innovative 
 method for reconstructing high-quality 3D scenes from a single RGB  image.
  Supporting open-vocabulary reconstruction, CAST excels in managing occlus
 ions, aligning objects accurately, and ensuring physical consistency with 
 the input, unlocking new possibilities in virtual content creation and rob
 otics.\n\nInterest Area: Research & Education\n\nRecording: Livestreamed, 
 Not Livestreamed, Recorded, Not Recorded\n\nRegistration Category: Full Co
 nference, Virtual Access, Tuesday\n\nSession Chair: Zhao Dong (Meta Realit
 y Labs Research)\n\n
END:VEVENT
END:VCALENDAR