ML Anthology

A Direct Method for Stereo Correspondence Based on Singular Value Decomposition

Maurizio Pilu
CVPR 1997 pp. 261-266
doi:10.1109/CVPR.1997.609330 /cvpr/1997/pilu1997cvpr-direct/

Abstract

This paper proposes a new algorithm for matching point features across pairs of images. Despite the well-known combinatorial complexity of the problem, this work shows that an acceptably good solution can be obtained directly by singular value decomposition of an appropriate correspondence strength matrix. The approach draws from the method proposed previously but, besides suggesting its usefulness for stereo matching, in this work a correlation-weighted proximity function is used as correspondence strength to specifically cater for real images.

CVPR Semantic Scholar

Cite

Text

Pilu. "A Direct Method for Stereo Correspondence Based on Singular Value Decomposition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609330

Markdown

[Pilu. "A Direct Method for Stereo Correspondence Based on Singular Value Decomposition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/pilu1997cvpr-direct/) doi:10.1109/CVPR.1997.609330

BibTeX

@inproceedings{pilu1997cvpr-direct,
  title     = {{A Direct Method for Stereo Correspondence Based on Singular Value Decomposition}},
  author    = {Pilu, Maurizio},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {261-266},
  doi       = {10.1109/CVPR.1997.609330},
  url       = {https://mlanthology.org/cvpr/1997/pilu1997cvpr-direct/}
}