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:20260417T190156Z
LOCATION:West Building\, Rooms 118-120
DTSTART;TZID=America/Los_Angeles:20250812T112500
DTEND;TZID=America/Los_Angeles:20250812T113500
UID:siggraph_SIGGRAPH 2025_sess146_papers_572@linklings.com
SUMMARY:LayerFlow: A Unified Model for Layer-aware Video Generation
DESCRIPTION:Sihui Ji (The University of Hong Kong); Hao Luo (DAMO Academy,
  Alibaba Group); and Xi Chen, Yuanpeng Tu, Yiyang Wang, and Hengshuang Zha
 o (The University of Hong Kong)\n\nWe propose LayerFlow,  a unified framew
 ork for layer-aware video generation, enabling seamless creation of transp
 arent foregrounds, clean backgrounds, and blended scenes. With multi-stage
  training and LoRA techniques improving layer-wise video quality with limi
 ted data, it also supports variants like video layer decomposition, genera
 ting backgrounds for given foregrounds and vice versa.\n\nInterest Area: R
 esearch & Education\n\nRecording: Livestreamed, Not Livestreamed, Recorded
 , Not Recorded\n\nRegistration Category: Full Conference, Virtual Access, 
 Tuesday\n\nSession Chair: Li-Yi Wei (Adobe Research)\n\n
END:VEVENT
END:VCALENDAR