Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds. The algorithm is based on minimizing the Frobenius distance between two elements of the Grassmannian. For this purpose, an indefinite relaxation of the Quadratic Assignment Problem (QAP) is used, and several approaches to affine feature matching are studied and compared. Experiments demonstrate that RoAM is more robust to noise and point discrepancy than previous methods.
@article{arxiv.2303.02698,
title = {Robust affine point matching via quadratic assignment on Grassmannians},
author = {Alexander Kolpakov and Michael Werman},
journal= {arXiv preprint arXiv:2303.02698},
year = {2024}
}
Comments
9 pages, 23 figures ; GitHub repository at https://github.com/sashakolpakov/roam ; added comparison to GrassGraph (https://doi.org/10.1109/TIP.2019.2959722); notably, GrassGraph quickly loses accuracy on our test examples with noise and occlusion ; to appear in Pattern Recognition Letters