Invariance and equivariance to the rotation group have been widely discussed in the 3D
deep learning community for pointclouds. Yet most proposed methods either use complex …

Traditional unlearnable strategies have been proposed to prevent unauthorized users from
training on the 2D image data. With more 3D point cloud data containing sensitivity …

We consider the deep point cloud analysis tasks where the inputs of the networks are
randomly rotated. Recent progress in rotation-invariant point cloud analysis is mainly driven …

Equivariance has been a long-standing concern in various fields ranging from computer
vision to physical modeling. Most previous methods struggle with generality, simplicity, and …

Learning pose invariant representation is a fundamental problem in shape analysis. Most
existing deep learning algorithms for 3D shape analysis are not robust to rotations and are …

Recent progress in introducing rotation invariance (RI) to 3D deep learning methods is
mainly made by designing RI features to replace 3D coordinates as input. The key to this …

Robust point cloud classification is crucial for real-world applications, as consumer-type 3D
sensors often yield partial and noisy data, degraded by various artifacts. In this work we …

Point cloud classifiers with rotation robustness have been widely discussed in the 3D deep
learning community. Most proposed methods either use rotation invariant descriptors as …

This study proposes a set of generic rules to revise existing neural networks for 3D point
cloud processing to rotation-equivariant quaternion neural networks (REQNNs), in order to …

Efficiency and robustness are increasingly needed for applications on 3D point clouds, with
the ubiquitous use of edge devices in scenarios like autonomous driving and robotics, which …