BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171530Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241203T170500
DTEND;TZID=Asia/Tokyo:20241203T171600
UID:siggraphasia_SIGGRAPH Asia 2024_sess111_papers_1192@linklings.com
SUMMARY:Perspective-Aligned AR Mirror with Under-Display Camera
DESCRIPTION:Jian Wang, Sizhuo Ma, Karl Bayer, Yi Zhang, Peihao Wang, and B
 ing Zhou (Snap Inc.); Shree Nayar (Columbia University); and Gurunandan Kr
 ishnan (Snap Inc.)\n\nAugmented reality (AR) mirrors are novel displays th
 at have great potential for commercial applications such as virtual appare
 l try-on. Typically the camera is placed beside the display, leading to di
 storted perspectives during user interaction. In this paper, we present a 
 novel approach to address this problem by placing the camera behind a tran
 sparent display, thereby providing users with a perspective-aligned experi
 ence. Simply placing the camera behind the display can compromise image qu
 ality due to optical effects. We meticulously analyze the image formation 
 process, and present an image restoration algorithm that benefits from phy
 sics-based data synthesis and network design. Our method significantly imp
 roves image quality and outperforms existing methods especially on the und
 erexplored wire and backscatter artifacts. We then carefully design a full
  AR mirror system including display and camera selection, real-time proces
 sing pipeline, and mechanical design. Our user study demonstrates that the
  system is exceptionally well-received by users, highlighting its  advanta
 ges over existing camera configurations not only as an AR mirror, but also
  for video conferencing. Our work represents a step forward in the develop
 ment of AR mirrors, with potential applications in retail, cosmetics, fash
 ion, \etc. The image restoration dataset and code are available at https:/
 /perspective-armirror.github.io/.\n\nRegistration Category: Full Access, F
 ull Access Supporter\n\nLanguage Format: English Language\n\nSession Chair
 : Yifan Peng (The University of Hong Kong)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_1192&sess=sess111
END:VEVENT
END:VCALENDAR