We present a novel rotation invariant architecture operating directly on point cloud data. We demonstrate how rotation invariance can be injected into a recently proposed point-based PCNN architecture, on all layers of the network. This leads to invariance to both global shape transformations, and to local rotations on the level of patches or parts, useful when dealing with non-rigid objects. We achieve this by employing a spherical harmonics-based kernel at different layers of the network, which is guaranteed to be invariant to rigid motions. We also introduce a more efficient pooling operation for PCNN using space-partitioning data-structures. This results in a flexible, simple and efficient architecture that achieves accurate results on challenging shape analysis tasks, including classification and segmentation, without requiring data-augmentation typically employed by non-invariant approaches.
|Original language||English (US)|
|Title of host publication||2019 International Conference on 3D Vision (3DV)|
|Number of pages||10|
|State||Published - Oct 31 2019|
Bibliographical noteKAUST Repository Item: Exported on 2022-06-30
Acknowledged KAUST grant number(s): CRG-2017-3426
Acknowledgements: Parts of this work were supported by KAUST OSR Award No. CRG-2017-3426, a gift from the NVIDIA Corporation and the ERC Starting Grant StG-2017-758800 (EXPROTEA).
This publication acknowledges KAUST support, but has no KAUST affiliated authors.