BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163645Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T111500
DTEND;TZID=Australia/Melbourne:20231215T112500
UID:siggraphasia_SIGGRAPH Asia 2023_sess156_papers_458@linklings.com
SUMMARY:Intrinsic Harmonization for Illumination-Aware Image Compositing
DESCRIPTION:Chris Careaga, S. Mahdi H. Miangoleh, and Yağız Aksoy (Simon F
 raser University)\n\nDespite significant advancements in network-based ima
 ge harmonization techniques, there still exists a domain gap between train
 ing pairs and real-world composites encountered during inference. Most exi
 sting methods are trained to reverse global edits made on segmented image 
 regions, which fail to accurately capture the lighting inconsistencies bet
 ween the foreground and background commonly found in composited images. In
  this work, we introduce a self-supervised illumination harmonization appr
 oach formulated in the intrinsic image domain. First, we estimate a simple
  global lighting model from mid-level vision representations to generate a
  rough shading for the foreground region. A network then refines this infe
 rred shading to generate a harmonious re-shading that aligns with the back
 ground scene. In order to match the color appearance of the foreground and
  background, we utilize ideas from prior harmonization approaches to perfo
 rm global image edits in the albedo domain. To validate the effectiveness 
 of our approach, we present results on challenging real-world composites a
 nd conduct a user study to objectively measure the enhanced realism achiev
 ed compared to state-of-the-art harmonization methods.\n\nRegistration Cat
 egory: Full Access\n\nSession Chair: Sergi Pujades (National Institute for
  Research in Computer Science and Automation (INRIA), Université Grenoble 
 Alpes)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_458&sess=sess156
END:VEVENT
END:VCALENDAR