What can missing correspondences tell us about 3D structure and motion?

Practically all existing approaches to structure and motion computation use only positive image correspondences to verify the camera pose hypotheses. Incorrect epipolar geometries are solely detected by identifying outliers among the found correspondences. Ambiguous patterns in the images are often...

Full description

Saved in:
Bibliographic Details
Published in2008 IEEE Conference on Computer Vision and Pattern Recognition pp. 1 - 8
Main Authors Zach, C., Irschara, A., Bischof, H.
Format Conference Proceeding
LanguageEnglish
Japanese
Published IEEE 01.06.2008
Subjects
Bayesian methods
Cameras
Computer graphics
Computer vision
Engines
Geometry
Image reconstruction
Layout
Pipelines
Solid modeling
Online AccessGet full text

Cover

More Information
Summary:Practically all existing approaches to structure and motion computation use only positive image correspondences to verify the camera pose hypotheses. Incorrect epipolar geometries are solely detected by identifying outliers among the found correspondences. Ambiguous patterns in the images are often incorrectly handled by these standard methods. In this work we propose two approaches to overcome such problems. First, we apply non-monotone reasoning on view triplets using a Bayesian formulation. In contrast to two-view epipolar geometry, image triplets allow the prediction of features in the third image. Absence of these features (i.e. missing correspondences) enables additional inference about the view triplet. Furthermore, we integrate these view triplet handling into an incremental procedure for structure and motion computation. Thus, our approach is able to refine the maintained 3D structure when additional image data is provided.
ISBN:9781424422425
1424422426
ISSN:1063-6919
DOI:10.1109/CVPR.2008.4587707