Scene reconstruction from multiple cameras

Author

Szeliski, Richard

Author_Institution

Vision Technol. Group, Microsoft Corp., Redmond, WA, USA

Volume

1

fYear

2000

fDate

2000

Firstpage

13

Abstract

This paper reviews a number of previously developed stereo matching algorithms and representations. It focuses on techniques that are especially well suited for stereoscopic and 3-D imaging applications such as novel view generation and the mixing of live imagery with synthetic computer graphics. The paper reviews some approaches to the classic problem of recovering a depth map from two or more images. It then describes a number of newer representations (and their associated reconstruction algorithms), including volumetric representations, layered plane-plus-parallax representations, and multiple depth maps

Keywords

computer graphics; image matching; image reconstruction; image representation; stereo image processing; video cameras; video signal processing; 3D broadcast stream; 3D imaging applications; depth map recovery; image reconstruction algorithms; layered plane-plus-parallax representations; live imagery generation; multiple cameras; multiple depth maps; scene reconstruction; stereo image representations; stereo matching algorithms; stereoscopic imaging applications; synthetic computer graphics; video images; volumetric representations; Application software; Bayesian methods; Cameras; Color; Computer vision; Image reconstruction; Layout; Pixel; Reconstruction algorithms; Stereo vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2000. Proceedings. 2000 International Conference on

Conference_Location

Vancouver, BC

ISSN

1522-4880

Print_ISBN

0-7803-6297-7

Type

conf

DOI

10.1109/ICIP.2000.900880

Filename

900880