HARA: A Hierarchical Approach for Robust Rotation Averaging
Lists
Only you see this
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.
BibTeX
@inproceedings{lee2021hara,
author = {Seong Hun Lee and Javier Civera},
title = {{HARA: A Hierarchical Approach for Robust Rotation Averaging}},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2021},
doi = {10.1109/cvpr52688.2022.01532},
}| Robust Single Rotation Averaging | arXiv · 2020 |
| Rotation-Only Bundle Adjustment | CVPR · 2021 |
| End-to-End Rotation Averaging With Multi-Source Propagation | CVPR · 2021 |
| On the Robustness of Multi-View Rotation Averaging | arXiv · 2021 |
| Robust Single Rotation Averaging Revisited | arXiv · 2023 |
| NeuRoRA: Neural Robust Rotation Averaging | ECCV · 2020 |