Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning

Seungwook Kim, Chunghyun Park, Yoonwoo Jeong, Jaesik Park, Minsu Cho
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16787-16806, 2023.

Abstract

Learning to predict reliable characteristic orientations of 3D point clouds is an important yet challenging problem, as different point clouds of the same class may have largely varying appearances. In this work, we introduce a novel method to decouple the shape geometry and semantics of the input point cloud to achieve both stability and consistency. The proposed method integrates shape-geometry-based SO(3)-equivariant learning and shape-semantics-based SO(3)-invariant residual learning, where a final characteristic orientation is obtained by calibrating an SO(3)-equivariant orientation hypothesis using an SO(3)-invariant residual rotation. In experiments, the proposed method not only demonstrates superior stability and consistency but also exhibits state-of-the-art performances when applied to point cloud part segmentation, given randomly rotated inputs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-kim23t, title = {Stable and Consistent Prediction of 3{D} Characteristic Orientation via Invariant Residual Learning}, author = {Kim, Seungwook and Park, Chunghyun and Jeong, Yoonwoo and Park, Jaesik and Cho, Minsu}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {16787--16806}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/kim23t/kim23t.pdf}, url = {https://proceedings.mlr.press/v202/kim23t.html}, abstract = {Learning to predict reliable characteristic orientations of 3D point clouds is an important yet challenging problem, as different point clouds of the same class may have largely varying appearances. In this work, we introduce a novel method to decouple the shape geometry and semantics of the input point cloud to achieve both stability and consistency. The proposed method integrates shape-geometry-based SO(3)-equivariant learning and shape-semantics-based SO(3)-invariant residual learning, where a final characteristic orientation is obtained by calibrating an SO(3)-equivariant orientation hypothesis using an SO(3)-invariant residual rotation. In experiments, the proposed method not only demonstrates superior stability and consistency but also exhibits state-of-the-art performances when applied to point cloud part segmentation, given randomly rotated inputs.} }
Endnote
%0 Conference Paper %T Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning %A Seungwook Kim %A Chunghyun Park %A Yoonwoo Jeong %A Jaesik Park %A Minsu Cho %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-kim23t %I PMLR %P 16787--16806 %U https://proceedings.mlr.press/v202/kim23t.html %V 202 %X Learning to predict reliable characteristic orientations of 3D point clouds is an important yet challenging problem, as different point clouds of the same class may have largely varying appearances. In this work, we introduce a novel method to decouple the shape geometry and semantics of the input point cloud to achieve both stability and consistency. The proposed method integrates shape-geometry-based SO(3)-equivariant learning and shape-semantics-based SO(3)-invariant residual learning, where a final characteristic orientation is obtained by calibrating an SO(3)-equivariant orientation hypothesis using an SO(3)-invariant residual rotation. In experiments, the proposed method not only demonstrates superior stability and consistency but also exhibits state-of-the-art performances when applied to point cloud part segmentation, given randomly rotated inputs.
APA
Kim, S., Park, C., Jeong, Y., Park, J. & Cho, M.. (2023). Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:16787-16806 Available from https://proceedings.mlr.press/v202/kim23t.html.

Related Material