ELF-Nets: Deep Learning on Point Clouds Using Extended Laplacian Filter

We propose a deep learning framework for various 3D vision tasks, which takes a point cloud as input. The convolution is a basic operator for feature extraction in deep learning. However, it is not directly applicable to a point cloud, which is an irregular, unordered point set. This makes deep lear...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.156569-156581
Main Authors: Lee, Seon-Ho, Kim, Han-Ul, Kim, Chang-Su
Format: Article
Language:English
Subjects:
3D deep learning
Convolution
convolutional neural network
Deep learning
Feature extraction
Geophysical measurement techniques
Ground penetrating radar
Image filters
Image processing
Image segmentation
Laplacian filter
Machine learning
object classification
Operators (mathematics)
Point cloud
semantic part segmentation
Three dimensional models
Three-dimensional displays
Two dimensional displays
Weighting functions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a deep learning framework for various 3D vision tasks, which takes a point cloud as input. The convolution is a basic operator for feature extraction in deep learning. However, it is not directly applicable to a point cloud, which is an irregular, unordered point set. This makes deep learning on point clouds challenging. To address this issue, we propose the extended Laplacian filter (ELF) for point clouds, which adopts the design principles of discrete Laplacian filters in 2D image processing. In other words, ELF extends the Laplacian filters and has the following two properties: 1) it is a two-state filter using two filter matrices (one for a center point and the other for neighboring points), and 2) it employs a scalar weighting function to predict the relative importance of the neighboring points. Then, we develop ELF-Nets, which consist of ELF convolution layers and fully connected layers. Experimental results demonstrate that the proposed ELF-Nets are capable of recognizing the 3D shape of a point cloud effectively and efficiently. In particular, ELF-Nets provide better or comparable performances than the state-of-the-art techniques in both object classification and part segmentation tasks.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2949785