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:20260114T163650Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T170000
DTEND;TZID=Australia/Melbourne:20231212T171000
UID:siggraphasia_SIGGRAPH Asia 2023_sess162_papers_307@linklings.com
SUMMARY:SinMPI: Novel View Synthesis from a Single Image with Expanded Mul
 tiplane Images
DESCRIPTION:Guo Pu, Peng-Shuai Wang, and Zhouhui Lian (Wangxuan Institute 
 of Computer Technology, Peking University)\n\nSingle-image novel view synt
 hesis is a challenging and ongoing problem that aims to generate an infini
 te number of consistent views from a single input image. Although signific
 ant efforts have been made to advance the quality of generated novel views
 , less attention has been paid to the expansion of the underlying scene re
 presentation, which is crucial to the generation of realistic novel view i
 mages. This paper proposes SinMPI, a novel method that uses expanded multi
 plane images (MPIs) as the 3D scene representation to significantly expand
  the perspective range of MPIs and generate high-quality novel views from 
 a large multiplane space. The key idea of our method is to use Stable Diff
 usion~\cite{rombach2021highresolution} to generate out-of-view contents, p
 roject all scene contents into expanded multiplane images, and then optimi
 ze the multiplane images under the supervision of pseudo-multi-view data g
 enerated by a depth-aware warping and inpainting module. Both qualitative 
 and quantitative experiments have been conducted to validate the superiori
 ty of our method to the state of the art. Our code and data are available 
 at https://github.com/TrickyGo/SinMPI.\n\nRegistration Category: Full Acce
 ss\n\nSession Chair: Binh-Son Hua (Trinity College Dublin)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_307&sess=sess162
END:VEVENT
END:VCALENDAR