Symmetry-Robust 3D Orientation Estimation

Christopher Scarvelis, David Benhaim, Paul Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53115-53131, 2025.

Abstract

Orientation estimation is a fundamental task in 3D shape analysis which consists of estimating a shape’s orientation axes: its side-, up-, and front-axes. Using this data, one can rotate a shape into canonical orientation, where its orientation axes are aligned with the coordinate axes. Developing an orientation algorithm that reliably estimates complete orientations of general shapes remains an open problem. We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation and further demonstrate its efficacy on full-orientation estimation, where one seeks all three orientation axes. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes. We motivate our engineering contributions by theory describing fundamental obstacles to orientation estimation for rotationally-symmetric shapes, and show how our method avoids these obstacles.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-scarvelis25a, title = {Symmetry-Robust 3{D} Orientation Estimation}, author = {Scarvelis, Christopher and Benhaim, David and Zhang, Paul}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {53115--53131}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/scarvelis25a/scarvelis25a.pdf}, url = {https://proceedings.mlr.press/v267/scarvelis25a.html}, abstract = {Orientation estimation is a fundamental task in 3D shape analysis which consists of estimating a shape’s orientation axes: its side-, up-, and front-axes. Using this data, one can rotate a shape into canonical orientation, where its orientation axes are aligned with the coordinate axes. Developing an orientation algorithm that reliably estimates complete orientations of general shapes remains an open problem. We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation and further demonstrate its efficacy on full-orientation estimation, where one seeks all three orientation axes. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes. We motivate our engineering contributions by theory describing fundamental obstacles to orientation estimation for rotationally-symmetric shapes, and show how our method avoids these obstacles.} }
Endnote
%0 Conference Paper %T Symmetry-Robust 3D Orientation Estimation %A Christopher Scarvelis %A David Benhaim %A Paul Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-scarvelis25a %I PMLR %P 53115--53131 %U https://proceedings.mlr.press/v267/scarvelis25a.html %V 267 %X Orientation estimation is a fundamental task in 3D shape analysis which consists of estimating a shape’s orientation axes: its side-, up-, and front-axes. Using this data, one can rotate a shape into canonical orientation, where its orientation axes are aligned with the coordinate axes. Developing an orientation algorithm that reliably estimates complete orientations of general shapes remains an open problem. We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation and further demonstrate its efficacy on full-orientation estimation, where one seeks all three orientation axes. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes. We motivate our engineering contributions by theory describing fundamental obstacles to orientation estimation for rotationally-symmetric shapes, and show how our method avoids these obstacles.
APA
Scarvelis, C., Benhaim, D. & Zhang, P.. (2025). Symmetry-Robust 3D Orientation Estimation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:53115-53131 Available from https://proceedings.mlr.press/v267/scarvelis25a.html.

Related Material