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:20260114T163712Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T114000
DTEND;TZID=Australia/Melbourne:20231215T115500
UID:siggraphasia_SIGGRAPH Asia 2023_sess156_papers_442@linklings.com
SUMMARY:Efficient Hybrid Zoom using Camera Fusion on Mobile Phones
DESCRIPTION:Xiaotong Wu, Wei-Sheng Lai, and Yichang Shih (Google Inc.); Ch
 arles Herrmann and Michael Krainin (Google Research); Deqing Sun (Google);
  and Chia-Kai Liang (Google Inc.)\n\nDSLR cameras can achieve multiple zoo
 m levels via shifting lens distances or swapping lens types. However, thes
 e techniques are not possible on smartphone devices due to space constrain
 ts. Most smartphone manufacturers adopt a hybrid zoom system: commonly a W
 ide (W) camera at a low zoom level and a Telephoto (T) camera at a high zo
 om level. To simulate zoom levels between W and T, these systems crop and 
 digitally upsample images from W, leading to significant detail loss. In t
 his paper, we propose an efficient system for hybrid zoom super-resolution
  on mobile devices, which captures a synchronous pair of W and T shots and
  leverages machine learning models to align and transfer details from T to
  W. We further develop an adaptive blending method that accounts for depth
 -of-field mismatches, scene occlusion, flow uncertainty, and alignment err
 ors. To minimize the domain gap, we design a dual-phone camera rig to capt
 ure real-world inputs and ground-truths for supervised training. Our metho
 d generates a 12-megapixel image in 500ms on a mobile platform and compare
 s favorably against state-of-the-art methods under extensive evaluation on
  real-world scenarios.\n\nRegistration Category: Full Access\n\nSession Ch
 air: Sergi Pujades (National Institute for Research in Computer Science an
 d Automation (INRIA), Université Grenoble Alpes)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_442&sess=sess156
END:VEVENT
END:VCALENDAR