Projective Registration with Difference Decomposition
Abstract
Current methods for registering image regions perform well for simple transformations or the large image regions. In this paper, we present a new method that is better able to handle small image regions as they deform with non-linear transformations. We introduce difference decompositon, a novel approach to solving the registration problem. The method is a generalization of previous methods and can better handle non-linear transforms. Although the methods are general, we focus on projective transformations and introduce piecewise-projective transformations for modeling the motions of non-planar objects. We conclude with examples from our prototype implementation.
Cite
Text
Gleicher. "Projective Registration with Difference Decomposition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609345Markdown
[Gleicher. "Projective Registration with Difference Decomposition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/gleicher1997cvpr-projective/) doi:10.1109/CVPR.1997.609345BibTeX
@inproceedings{gleicher1997cvpr-projective,
title = {{Projective Registration with Difference Decomposition}},
author = {Gleicher, Michael},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1997},
pages = {331-337},
doi = {10.1109/CVPR.1997.609345},
url = {https://mlanthology.org/cvpr/1997/gleicher1997cvpr-projective/}
}