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:20240731T113500
DTEND;TZID=America/Denver:20240731T114500
UID:siggraph_SIGGRAPH 2024_sess130_papers_1160@linklings.com
SUMMARY:Matting by Generation
DESCRIPTION:Zhixiang Wang (University of Tokyo), Baiang Li (Hefei Universi
 ty of Technology), Jian Wang (Snap), Yu-Lun Liu (National Chiao Tung Unive
 rsity), Jinwei Gu (Chinese University of Hong Kong), Yung-Yu Chuang (Natio
 nal Taiwan University), and Shin'ichi Satoh (National Institute of Informa
 tics)\n\nThis paper redefines traditional regression-based matting as a ge
 nerative modeling challenge and harnesses the capabilities of latent diffu
 sion models enriched with extensive pre-trained knowledge to tackle this c
 hallenge. It not only produces mattes with superior resolution and detail 
 but is also versatile and can perform both guidance-free and guidance-base
 d matting.\n\nInterest Area: Research & Education\n\nRecording: Livestream
 ed, Recorded\n\nRegistration Category: Full Conference, Full Conference Su
 pporter, Virtual Access, Exhibitor Full Conference, Wednesday\n\nSession C
 hair: Yotam Gingold (George Mason University)\n\n
END:VEVENT
END:VCALENDAR