BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035312Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221209T140000
DTEND;TZID=Asia/Seoul:20221209T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess174_papers_488@linklings.com
SUMMARY:VIINTER: View Interpolation With Implicit Neural Representations o
 f Images
DESCRIPTION:Technical Communications, Technical Papers\n\nVIINTER: View In
 terpolation With Implicit Neural Representations of Images\n\nFeng, Jabbir
 eddy, Varshney\n\nWe present VIINTER, a method for view interpolation by i
 nterpolating the implicit neural representation (INR) of the captured imag
 es. We leverage the learned code vector associated with each image and int
 erpolate between these codes to achieve viewpoint transitions. We propose 
 several techniques that significantly enhance the interpolation quality. V
 IINTER signifies a new way to achieve view interpolation without construct
 ing 3D structure, estimating camera poses, or computing pixel corresponden
 ce. We validate the effectiveness of VIINTER on several multi-view scenes 
 with different types of camera layout and scene composition. As the develo
 pment of INR of images (as opposed to surface or volume) has centered arou
 nd tasks like image fitting and super-resolution, with VIINTER, we show it
 s capability for view interpolation and offer a promising outlook on using
  INR for image manipulation tasks.\n\nRegistration Category: FULL ACCESS, 
 ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_488&sess=sess17
 4
END:VEVENT
END:VCALENDAR