Hierarchically-Constrained Optical Flow

Ryan Kennedy, Camillo J. Taylor; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3340-3348

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Kennedy_2015_CVPR,
author = {Kennedy, Ryan and Taylor, Camillo J.},
title = {Hierarchically-Constrained Optical Flow},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}