Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

9-2019

Abstract

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks that generalizes poorly to arbitrary rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is also addressed by a binning approach seamlessly built into the convolution. This convolution operator then serves as the basic building block of a neural network that is robust to point clouds under 6-DoF transformations such as translation and rotation. Our experiment shows that our method performs with high accuracy in common scene understanding tasks such as object classification and segmentation. Compared to previous and concurrent works, most importantly, our method is able to generalize and achieve consistent results across different scenarios in which training and testing can contain arbitrary rotations. Our implementation is publicly available at our project page.

Keywords

Three-dimensional displays, Feature extraction, Deep learning, Task analysis, Neural networks, Training, Semantics

Discipline

Graphics and Human Computer Interfaces | OS and Networks

Research Areas

Information Systems and Management

Publication

Proceedings of the 2019 International Conference on 3D Vision (3DV), Quebec, Canada, September 16-19

First Page

204

Last Page

213

ISBN

9781728131313

Identifier

10.1109/3dv.2019.00031

Publisher

IEEE

City or Country

Quebec City, QC, Canada

Additional URL

https://doi.org/10.1109/3dv.2019.00031

Download

Share

COinS