Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

08/17/2019
by   Zhiyuan Zhang, et al.
0

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 being trained with data augmented with 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 6DoF 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 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.

READ FULL TEXT

page 8

page 13

research
08/07/2020

Global Context Aware Convolutions for 3D Point Cloud Understanding

Recent advances in deep learning for 3D point clouds have shown great pr...
research
11/18/2020

Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis

In this paper we propose a rotation-invariant deep network for point clo...
research
12/07/2020

Rotation-Invariant Point Convolution With Multiple Equivariant Alignments

Recent attempts at introducing rotation invariance or equivariance in 3D...
research
12/02/2020

Sparse Convolutions on Continuous Domains for Point Cloud and Event Stream Networks

Image convolutions have been a cornerstone of a great number of deep lea...
research
08/24/2019

Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes

Existing networks directly learn feature representations on 3D point clo...
research
12/23/2021

Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?

Geometric deep learning, i.e., designing neural networks to handle the u...
research
01/02/2021

Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks

Point cloud analysis is an area of increasing interest due to the develo...

Please sign up or login with your details

Forgot password? Click here to reset