HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Effective Rotation-invariant Point CNN with Spherical Harmonics kernels

Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [35 references]  Display  Hide  Download

Contributor : Yann Ponty Connect in order to contact the contributor
Submitted on : Monday, September 16, 2019 - 9:27:59 AM
Last modification on : Monday, March 1, 2021 - 3:19:27 AM


Files produced by the author(s)


  • HAL Id : hal-02167454, version 2



Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty, Maks Ovsjanikov. Effective Rotation-invariant Point CNN with Spherical Harmonics kernels. 3DV - International Conference on 3D Vision - 2019, Sep 2019, Québec City, Canada. ⟨hal-02167454v2⟩



Record views


Files downloads