An iterative quantum approach for transformation estimation from point sets
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Natacha Kuete Meli, Florian Mannel and Jan Lellmann
Abstract:
We propose an iterative method for estimating rigid transformations from point sets using adiabatic quantum computation. Compared to existing quantum approaches, our method relies on an adaptive scheme to solve the problem to high precision, and does not suffer from inconsistent rotation matrices. Experimentally, our method performs robustly on several 2D and 3D datasets even with high outlier ratio.
Ressources
Cite [BibTex]:
@INPROCEEDINGS{9879968,
author={Meli, Natacha Kuete and Mannel, Florian and Lellmann, Jan},
booktitle={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
title={An Iterative Quantum Approach for Transformation Estimation from Point Sets},
year={2022},
volume={},
number={},
pages={519-527},
keywords={Computer vision;Three-dimensional displays;Annealing;Estimation;Quantum annealing;Pattern recognition;Iterative methods;Optimization methods; Computer vision theory; Low-level vision; Motion and tracking; Others},
doi={10.1109/CVPR52688.2022.00061}
}