Correspondence Expansion for Wide Baseline Stereo

Steele, Kevin L.; Egbert, Parris K.

doi:10.1109/CVPR.2005.113

Correspondence Expansion for Wide Baseline Stereo

Kevin L. Steele, Parris K. Egbert

CVPR 2005 pp. 1055-1062

doi:10.1109/CVPR.2005.113 /cvpr/2005/steele2005cvpr-correspondence/

Abstract

We present a new method for generating large numbers of accurate point correspondences between two wide baseline images. This is important for structure-from-motion algorithms, which rely on many correct matches to reduce error in the derived geometric structure. Given a small initial correspondence set we iteratively expand the set with nearby points exhibiting strong affine correlation, and then we constrain the set to an epipolar geometry using RANSAC. A key point to our algorithm is to allow a high error tolerance in the constraint, allowing the correspondence set to expand into many areas of an image before applying a lower error tolerance constraint. We show that this method successfully expands a small set of initial matches, and we demonstrate it on a variety of image pairs.

CVPR Semantic Scholar

Cite

Text

Steele and Egbert. "Correspondence Expansion for Wide Baseline Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.113

Markdown

[Steele and Egbert. "Correspondence Expansion for Wide Baseline Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/steele2005cvpr-correspondence/) doi:10.1109/CVPR.2005.113

BibTeX

@inproceedings{steele2005cvpr-correspondence,
  title     = {{Correspondence Expansion for Wide Baseline Stereo}},
  author    = {Steele, Kevin L. and Egbert, Parris K.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {1055-1062},
  doi       = {10.1109/CVPR.2005.113},
  url       = {https://mlanthology.org/cvpr/2005/steele2005cvpr-correspondence/}
}