ML Anthology

A General Framework and New Alignment Criterion for Dense Optical Flow

Rami Ben-Ari, Nir A. Sochen
CVPR 2006 pp. 529-536
doi:10.1109/CVPR.2006.25 /cvpr/2006/benari2006cvpr-general/

Abstract

The problem of dense optical flow computation is addressed from a variational viewpoint. A new geometric framework is introduced. It unifies previous art and yields new efficient methods. Along with the framework a new alignment criterion suggests itself. It is shown that the alignment between the gradients of the optical flow components and between the latter and the intensity gradients is an important measure of the flow's quality. Adding this criterion as a requirement in the optimization process improves the resulting flow. This is demonstrated in synthetic and real sequences.

CVPR Semantic Scholar

Cite

Text

Ben-Ari and Sochen. "A General Framework and New Alignment Criterion for Dense Optical Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.25

Markdown

[Ben-Ari and Sochen. "A General Framework and New Alignment Criterion for Dense Optical Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/benari2006cvpr-general/) doi:10.1109/CVPR.2006.25

BibTeX

@inproceedings{benari2006cvpr-general,
  title     = {{A General Framework and New Alignment Criterion for Dense Optical Flow}},
  author    = {Ben-Ari, Rami and Sochen, Nir A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {529-536},
  doi       = {10.1109/CVPR.2006.25},
  url       = {https://mlanthology.org/cvpr/2006/benari2006cvpr-general/}
}