Local Shape Estimation from a Single Keypoint
Abstract
This paper presents a novel approach to estimate local homography of points belong to a given surface. While others works attempt this by using iterative algorithms developed for template matching, our method introduces a direct estimation of the transformation. It performs the following steps. First, a training set of features captures appearance and geometry information about keypoints taken from multiple views of the surface. Then incoming keypoints are matched against the training set in order to retrieve a cluster of features representing their identity. Finally the retrieved clusters are used to estimate the local pose of the regions around keypoints. Thanks to the high accuracy, outliers and bad estimates are filtered out by multiscale Summed Square Difference (SSD) test.
Cite
Text
Del Bimbo et al. "Local Shape Estimation from a Single Keypoint." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010. doi:10.1109/CVPRW.2010.5543277Markdown
[Del Bimbo et al. "Local Shape Estimation from a Single Keypoint." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010.](https://mlanthology.org/cvprw/2010/bimbo2010cvprw-local/) doi:10.1109/CVPRW.2010.5543277BibTeX
@inproceedings{bimbo2010cvprw-local,
title = {{Local Shape Estimation from a Single Keypoint}},
author = {Del Bimbo, Alberto and Franco, Fernando and Pernici, Federico},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2010},
pages = {23-28},
doi = {10.1109/CVPRW.2010.5543277},
url = {https://mlanthology.org/cvprw/2010/bimbo2010cvprw-local/}
}