Learning with 3D rotations, a hitchhiker’s guide to SO(3)

Andreas René Geist, Jonas Frey, Mikel Zhobro, Anna Levina, Georg Martius
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15331-15350, 2024.

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 this Paper

BibTeX
@InProceedings{pmlr-v235-geist24a, title = {Learning with 3{D} rotations, a hitchhiker’s guide to {SO}(3)}, author = {Geist, Andreas Ren\'{e} and Frey, Jonas and Zhobro, Mikel and Levina, Anna and Martius, Georg}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {15331--15350}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/geist24a/geist24a.pdf}, url = {https://proceedings.mlr.press/v235/geist24a.html}, 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.} }
Endnote
%0 Conference Paper %T Learning with 3D rotations, a hitchhiker’s guide to SO(3) %A Andreas René Geist %A Jonas Frey %A Mikel Zhobro %A Anna Levina %A Georg Martius %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-geist24a %I PMLR %P 15331--15350 %U https://proceedings.mlr.press/v235/geist24a.html %V 235 %X 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.
APA
Geist, A.R., Frey, J., Zhobro, M., Levina, A. & Martius, G.. (2024). Learning with 3D rotations, a hitchhiker’s guide to SO(3). Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:15331-15350 Available from https://proceedings.mlr.press/v235/geist24a.html.

Related Material