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 118-120
DTSTART;TZID=America/Los_Angeles:20250813T114500
DTEND;TZID=America/Los_Angeles:20250813T115500
UID:siggraph_SIGGRAPH 2025_sess152_papers_224@linklings.com
SUMMARY:Instance Segmentation of Scene Sketches Using Natural Image Priors
DESCRIPTION:Mia Tang (Stanford University, Carnegie Mellon University); Ya
 el Vinker (Computer Science and Artificial Intelligence Laboratory (CSAIL)
 , Massachusetts Institute of Technology (MIT)); Chuan Yan and Lvmin Zhang 
 (Stanford University); and Maneesh Agrawala (Stanford University, Roblox R
 esearch)\n\nINKi enables instance segmentation for scene sketches by adapt
 ing image segmentation models with class-agnostic tuning and depth-based r
 efinement. We introduce a new dataset INK-scene with diverse styles and de
 monstrate layered sketch organization for advanced editing, including inpa
 inting occluded instances—paving the way for robust, editable sketch under
 standing.\n\nInterest Area: Research & Education\n\nRecording: Livestreame
 d, Not Livestreamed, Recorded, Not Recorded\n\nRegistration Category: Full
  Conference, Virtual Access, Wednesday\n\nSession Chair: Or Patashnik (Tel
  Aviv University, Snap Research)\n\n
END:VEVENT
END:VCALENDAR