Hierarchically-Constrained Optical Flow

CVPR 2015

doi:10.1109/CVPR.2015.7298955 /cvpr/2015/kennedy2015cvpr-hierarchicallyconstrained/

Abstract

This paper presents a novel approach to solving optical flow problems using a discrete, tree-structured MRF derived from a hierarchical segmentation of the image. Our method can be used to find globally optimal matching solutions even for problems involving very large motions. Experiments demonstrate that our approach is competitive on the MPI-Sintel dataset and that it can significantly outperform existing methods on problems involving large motions.

PDF CVPR Semantic Scholar

Cite

Text

Kennedy and Taylor. "Hierarchically-Constrained Optical Flow." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298955

Markdown

[Kennedy and Taylor. "Hierarchically-Constrained Optical Flow." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/kennedy2015cvpr-hierarchicallyconstrained/) doi:10.1109/CVPR.2015.7298955

BibTeX

@inproceedings{kennedy2015cvpr-hierarchicallyconstrained,
  title     = {{Hierarchically-Constrained Optical Flow}},
  author    = {Kennedy, Ryan and Taylor, Camillo J.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7298955},
  url       = {https://mlanthology.org/cvpr/2015/kennedy2015cvpr-hierarchicallyconstrained/}
}