PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

by   Yang You, et al.

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Point-wise Rotation Invariant Network, focusing on rotation invariant feature extraction in point clouds analysis. We construct spherical signals by Density Aware Adaptive Sampling to deal with distorted point distributions in spherical space. Spherical Voxel Convolution and Point Re-sampling are proposed to extract rotation invariant features for each point. In addition, we extend PRIN to a sparse version called SPRIN, which directly operates on sparse point clouds. Both PRIN and SPRIN can be applied to tasks ranging from object classification, part segmentation, to 3D feature matching and label alignment. Results show that, on the dataset with randomly rotated point clouds, SPRIN demonstrates better performance than state-of-the-art methods without any data augmentation. We also provide thorough theoretical proof and analysis for point-wise rotation invariance achieved by our methods. Our code is available on


page 7

page 8


PRIN: Pointwise Rotation-Invariant Network

In recent years, point clouds have earned quite some research interests ...

TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Classification

Rotation invariance is an important requirement for the analysis of 3D p...

Edge-Selective Feature Weaving for Point Cloud Matching

This paper tackles the problem of accurately matching the points of two ...

Effective Rotation-invariant Point CNN with Spherical Harmonics kernels

We present a novel rotation invariant architecture operating directly on...

Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds

We introduce tensor field networks, which are locally equivariant to 3D ...

Density-invariant Features for Distant Point Cloud Registration

Registration of distant outdoor LiDAR point clouds is crucial to extendi...

Code Repositories


Pointwise Rotation-Invariant Network (AAAI 2020)

view repo


PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

view repo

Please sign up or login with your details

Forgot password? Click here to reset