Learning with 3D Rotations, a Hitchhiker’s Guide to SO(3)
Abstract
Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. This paper acts as a survey and guide through rotation representations. We walk through their properties that harm or benefit deep learning with gradient-based optimization. By consolidating insights from rotation-based learning, we provide a comprehensive overview of learning functions with rotation representations. We provide guidance on selecting representations based on whether rotations are in the model’s input or output and whether the data primarily comprises small angles.
Cite
Text
Geist et al. "Learning with 3D Rotations, a Hitchhiker’s Guide to SO(3)." International Conference on Machine Learning, 2024.Markdown
[Geist et al. "Learning with 3D Rotations, a Hitchhiker’s Guide to SO(3)." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/geist2024icml-learning/)BibTeX
@inproceedings{geist2024icml-learning,
title = {{Learning with 3D Rotations, a Hitchhiker’s Guide to SO(3)}},
author = {Geist, Andreas René and Frey, Jonas and Zhobro, Mikel and Levina, Anna and Martius, Georg},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {15331-15350},
volume = {235},
url = {https://mlanthology.org/icml/2024/geist2024icml-learning/}
}