HARA: A Hierarchical Approach for Robust Rotation Averaging
Abstract
We propose a novel hierarchical approach for multiple rotation averaging, dubbed HARA. Our method incrementally initializes the rotation graph based on a hierarchy of triplet support. The key idea is to build a spanning tree by prioritizing the edges with many strong triplet supports and gradually adding those with weaker and fewer supports. This reduces the risk of adding outliers in the spanning tree. As a result, we obtain a robust initial solution that enables us to filter outliers prior to nonlinear optimization. With minimal modification, our approach can also integrate the knowledge of the number of valid 2D-2D correspondences. We perform extensive evaluations on both synthetic and real datasets, demonstrating state-of-the-art results.
Cite
Text
Lee and Civera. "HARA: A Hierarchical Approach for Robust Rotation Averaging." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.01532Markdown
[Lee and Civera. "HARA: A Hierarchical Approach for Robust Rotation Averaging." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/lee2022cvpr-hara/) doi:10.1109/CVPR52688.2022.01532BibTeX
@inproceedings{lee2022cvpr-hara,
title = {{HARA: A Hierarchical Approach for Robust Rotation Averaging}},
author = {Lee, Seong Hun and Civera, Javier},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2022},
pages = {15777-15786},
doi = {10.1109/CVPR52688.2022.01532},
url = {https://mlanthology.org/cvpr/2022/lee2022cvpr-hara/}
}