Bilateral Functions for Global Motion Modeling
Abstract
This paper proposes modeling motion in a bilateral domain that augments spatial information with the motion itself. We use the bilateral domain to reformulate a piecewise smooth constraint as continuous global modeling constraint. The resultant model can be robustly computed from highly noisy scattered feature points using a global minimization. We demonstrate how the model can reliably obtain large numbers of good quality correspondences over wide baselines, while keeping outliers to a minimum.
Cite
Text
Lin et al. "Bilateral Functions for Global Motion Modeling." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10593-2_23Markdown
[Lin et al. "Bilateral Functions for Global Motion Modeling." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/lin2014eccv-bilateral/) doi:10.1007/978-3-319-10593-2_23BibTeX
@inproceedings{lin2014eccv-bilateral,
title = {{Bilateral Functions for Global Motion Modeling}},
author = {Lin, Wen-Yan Daniel and Cheng, Ming-Ming and Lu, Jiangbo and Yang, Hongsheng and Do, Minh N. and Torr, Philip H. S.},
booktitle = {European Conference on Computer Vision},
year = {2014},
pages = {341-356},
doi = {10.1007/978-3-319-10593-2_23},
url = {https://mlanthology.org/eccv/2014/lin2014eccv-bilateral/}
}