Optical Flow Requires Multiple Strategies (but Only One Network)

CVPR 2017

doi:10.1109/CVPR.2017.732 /cvpr/2017/schuster2017cvpr-optical/

Abstract

We show that the matching problem that underlies optical flow requires multiple strategies, depending on the amount of image motion and other factors. We then study the implications of this observation on training a deep neural network for representing image patches in the context of descriptor based optical flow. We propose a metric learning method, which selects suitable negative samples based on the nature of the true match. This type of training produces a network that displays multiple strategies depending on the input and leads to state of the art results on the KITTI 2012 and KITTI 2015 optical flow benchmarks.

PDF CVPR Semantic Scholar

Cite

Text

Schuster et al. "Optical Flow Requires Multiple Strategies (but Only One Network)." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.732

Markdown

[Schuster et al. "Optical Flow Requires Multiple Strategies (but Only One Network)." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/schuster2017cvpr-optical/) doi:10.1109/CVPR.2017.732

BibTeX

@inproceedings{schuster2017cvpr-optical,
  title     = {{Optical Flow Requires Multiple Strategies (but Only One Network)}},
  author    = {Schuster, Tal and Wolf, Lior and Gadot, David},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.732},
  url       = {https://mlanthology.org/cvpr/2017/schuster2017cvpr-optical/}
}