Virtual view synthesis using RGB-D cameras

Chun Liang Chien, Tzu Chin Lee, Hsueh-Ming Hang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A view synthesis problem is to generate a virtual view based on the given one or multiple views and their associated depth maps. We adopt the depth image based rendering (DIBR) approach in this paper for synthesizing the new views. No explicit 3D modeling is involved. Another component of this study is the popular commodity RGB-D (color plus depth) cameras. The color and depth images captured by a pair of RGB-D cameras (Microsoft Kinect for Windows v2) are our inputs to synthesize intermediate virtual views between these two cameras. Several methods include depth to color warping, disocclusion filling, and color to color warping are adopted and designed to achieve this target. One of our major contributions is a new disocclusion detection algorithm proposed to improve the disocclusion filling result. Furthermore, an improved camera calibration method is proposed to make use of the additional depth information. Good quality synthesized views are shown at the end.

Original languageEnglish
Title of host publication2016 3DTV-Conference
Subtitle of host publicationThe True Vision - Capture, Transmission and Display of 3D Video, 3DTV-CON 2016
PublisherIEEE Computer Society
ISBN (Electronic)9781509033133
DOIs
StatePublished - 22 Aug 2016
Event2016 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video, 3DTV-CON 2016 - Hamburg, Germany
Duration: 4 Jul 20166 Jul 2016

Publication series

Name3DTV-Conference
Volume2016-August
ISSN (Print)2161-2021
ISSN (Electronic)2161-203X

Conference

Conference2016 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video, 3DTV-CON 2016
CountryGermany
CityHamburg
Period4/07/166/07/16

Keywords

  • backward warping
  • camera calibration
  • depth map
  • disocclusion filling
  • Kinect
  • View synthesis

Fingerprint Dive into the research topics of 'Virtual view synthesis using RGB-D cameras'. Together they form a unique fingerprint.

Cite this