filename     : Rov18b.pdf
entry        : inproceedings
conference   : Conference on Computer Vision and Pattern Recognition
pages        : 
year         : 2018
month        : June
title        : A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation
subtitle     :
author       : Riccardo Roveri and Lukas Rahmann and A. Cengiz \"{O}ztireli and Markus Gross
booktitle    : 
ISSN/ISBN    :
editor       : 
publisher    : 
publ.place   :
volume       :
issue        :
language     : english
keywords     : computer vision, point processing
abstract     : We propose a novel neural network architecture for point cloud classification. Our key idea is to automatically transform the 3D unordered input data into a set of useful 2D
depth images, and classify them by exploiting well performing image classification CNNs. We present new differentiable module designs to generate depth images from a point cloud. These modules can be combined with any network architecture for processing point clouds. We utilize them in combination with state-of-the-art classification networks, and get results competitive with the state of the art in point cloud classification. Furthermore, our architecture automatically produces informative images representing the input point cloud, which could be used for further applications such as point cloud visualization.