PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (3) · 3418-3426
DOI: 10.1609/aaai.v37i3.25450 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Dingxin Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent interest in point cloud analysis has led rapid progress in designing deep learning methods for 3D models. However, state-of-the-art models are not robust to rotations, which remains an unknown prior to real applications and harms the model performance. In this work, we introduce a novel Patch-wise Rotation-invariant network (PaRot), which achieves rotation invariance via feature disentanglement and produces consistent predictions for samples with arbitrary rotations. Specifically, we design a siamese training module which disentangles rotation invariance and equivariance from patches defined over different scales, e.g., the local geometry and global shape, via a pair of rotations. However, our disentangled invariant feature loses the intrinsic pose information of each patch. To solve this problem, we propose a rotation-invariant geometric relation to restore the relative pose with equivariant information for patches defined over different scales. Utilising the pose information, we propose a hierarchical module which implements intra-scale and inter-scale feature aggregation for 3D shape learning. Moreover, we introduce a pose-aware feature propagation process with the rotation-invariant relative pose information embedded. Experiments show that our disentanglement module extracts high-quality rotation-robust features and the proposed lightweight model achieves competitive results in rotated 3D object classification and part segmentation tasks.
Zitieren
APA
Zhang, D., Yu, J., Zhang, C., & Cai, W. (2023). PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3418-3426. https://doi.org/10.1609/aaai.v37i3.25450
Vancouver
Zhang D, Yu J, Zhang C, Cai W. PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(3):3418-3426. doi:10.1609/aaai.v37i3.25450
BibTeX
@article{Zhang2023,
author = {Zhang, Dingxin and Yu, Jianhui and Zhang, Chaoyi and Cai, Weidong},
title = {PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {3},
pages = {3418--3426},
doi = {10.1609/aaai.v37i3.25450}
}
EUVIMED