Spherical Convolutional Neural Network for 3D Point Clouds

05/21/2018
by   Haun Lei, et al.
0

We propose a neural network for 3D point cloud processing that exploits `spherical' convolution kernels and octree partitioning of space. The proposed metric-based spherical kernels systematically quantize point neighborhoods to identify local geometric structures in data, while maintaining the properties of translation-invariance and asymmetry. The network architecture itself is guided by octree data structuring that takes full advantage of the sparse nature of irregular point clouds. We specify spherical kernels with the help of neurons in each layer that in turn are associated with spatial locations. We exploit this association to avert dynamic kernel generation during network training, that enables efficient learning with high resolution point clouds. We demonstrate the utility of the spherical convolutional neural network for 3D object classification on standard benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/28/2019

Octree guided CNN with Spherical Kernels for 3D Point Clouds

We propose an octree guided neural network architecture and spherical co...
research
09/20/2019

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

We propose a spherical kernel for efficient graph convolution of 3D poin...
research
05/24/2023

Deep Equivariant Hyperspheres

This paper presents an approach to learning nD features equivariant unde...
research
12/19/2019

Tangent Images for Mitigating Spherical Distortion

In this work, we propose "tangent images," a spherical image representat...
research
03/18/2021

Concentric Spherical GNN for 3D Representation Learning

Learning 3D representations that generalize well to arbitrarily oriented...
research
04/05/2018

Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor

Object retrieval and classification in point cloud data is challenged by...
research
03/20/2018

Flex-Convolution (Deep Learning Beyond Grid-Worlds)

The goal of this work is to enable deep neural networks to learn represe...

Please sign up or login with your details

Forgot password? Click here to reset