ML Anthology

Fast Variable Window for Stereo Correspondence Using Integral Images

Olga Veksler
CVPR 2003 pp. 556-564
doi:10.1109/CVPR.2003.1211403 /cvpr/2003/veksler2003cvpr-fast/

Abstract

We develop a fast and accurate variable window approach. The two main ideas for achieving accuracy are choosing a useful range of window sizes/shapes for evaluation and developing a new window cost which is particularly suitable for comparing windows of different sizes. The speed of our approach is due to the integral image technique, which allows computation of our window cost over any rectangular window in constant time, regardless of window size. Our method ranks in the top four on the Middlebury stereo database with ground truth, and performs best out of methods which have comparable efficiency.

CVPR Semantic Scholar

Cite

Text

Veksler. "Fast Variable Window for Stereo Correspondence Using Integral Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211403

Markdown

[Veksler. "Fast Variable Window for Stereo Correspondence Using Integral Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/veksler2003cvpr-fast/) doi:10.1109/CVPR.2003.1211403

BibTeX

@inproceedings{veksler2003cvpr-fast,
  title     = {{Fast Variable Window for Stereo Correspondence Using Integral Images}},
  author    = {Veksler, Olga},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {556-564},
  doi       = {10.1109/CVPR.2003.1211403},
  url       = {https://mlanthology.org/cvpr/2003/veksler2003cvpr-fast/}
}