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 …

We present RoReg, a novel point cloud registration framework that fully exploits oriented
descriptors and estimated local rotations in the whole registration pipeline. Previous …

In this paper, we propose a novel local descriptor-based framework, called You Only
Hypothesize Once (YOHO), for the registration of two unaligned point clouds. In contrast to …

Motivated by the vast success of deep convolutional networks, there is a great interest in
generalizing convolutions to non-Euclidean manifolds. A major complication in comparison …

Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have
conducted experiments on synthetic datasets with well-aligned data; while real-world point …

Recently, many deep neural networks were designed to process 3D point clouds, but a
common drawback is that rotation invariance is not ensured, leading to poor generalization …

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 …

Detecting symmetrical properties is a fundamental task in 3D shape analysis. In the case of
a 3D model with planar symmetries, each point has a corresponding mirror point wrt a …

Quaternions are extensively used in several fields including physics, applied mathematics,
computer graphics, and control systems because of their notable and unique characteristics …

In recent years, neural implicit representations have made remarkable progress in modeling
of 3D shapes with arbitrary topology. In this work, we address two key limitations of such …