Generalized Convolutional Neural Networks for Point Cloud Data

TL;DR

This paper introduces a novel neural network architecture that directly processes point cloud data using a convolutional approach, enabling efficient 3D data analysis without extensive feature engineering.

Contribution

It presents a new method to apply convolutional neural networks directly to point clouds by mapping nearest neighbors and weighting spatial relationships, simplifying 3D data processing.

Findings

Achieves efficient processing of point clouds with few parameters

Works directly on raw point cloud data without feature engineering

Closely resembles traditional CNN behavior in 3D space

Abstract

The introduction of cheap RGB-D cameras, stereo cameras, and LIDAR devices has given the computer vision community 3D information that conventional RGB cameras cannot provide. This data is often stored as a point cloud. In this paper, we present a novel method to apply the concept of convolutional neural networks to this type of data. By creating a mapping of nearest neighbors in a dataset, and individually applying weights to spatial relationships between points, we achieve an architecture that works directly with point clouds, but closely resembles a convolutional neural net in both design and behavior. Such a method bypasses the need for extensive feature engineering, while proving to be computationally efficient and requiring few parameters.