ML Anthology

Classification and Evaluation of Cost Aggregation Methods for Stereo Correspondence

Federico Tombari, Stefano Mattoccia, Luigi Di Stefano, Elisa Addimanda
CVPR 2008
doi:10.1109/CVPR.2008.4587677 /cvpr/2008/tombari2008cvpr-classification/

Abstract

In the last decades several cost aggregation methods
\naimed at improving the robustness of stereo correspondence
\nwithin local and global algorithms have been proposed.
\nGiven the recent developments and the lack of an appropriate
\ncomparison, in this paper we survey, classify and
\ncompare experimentally on a standard data set the main
\ncost aggregation approaches proposed in literature. The experimental
\nevaluation addresses both accuracy and computational
\nrequirements, so as to outline the best performing
\nmethods under these two criteria.

PDF CVPR Semantic Scholar

Cite

Text

Tombari et al. "Classification and Evaluation of Cost Aggregation Methods for Stereo Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587677

Markdown

[Tombari et al. "Classification and Evaluation of Cost Aggregation Methods for Stereo Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/tombari2008cvpr-classification/) doi:10.1109/CVPR.2008.4587677

BibTeX

@inproceedings{tombari2008cvpr-classification,
  title     = {{Classification and Evaluation of Cost Aggregation Methods for Stereo Correspondence}},
  author    = {Tombari, Federico and Mattoccia, Stefano and Di Stefano, Luigi and Addimanda, Elisa},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587677},
  url       = {https://mlanthology.org/cvpr/2008/tombari2008cvpr-classification/}
}