Pointwise Convolutional Neural Networks

Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently. However, the capability of using point clouds with convolutional neural network has been so far not fully explored. In this paper, we present a convolutional neural network fo...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 984 - 993
Main Authors Hua, Binh-Son, Tran, Minh-Khoi, Yeung, Sai-Kit
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Convolution
Kernel
Object recognition
Semantics
Shape
Task analysis
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently. However, the capability of using point clouds with convolutional neural network has been so far not fully explored. In this paper, we present a convolutional neural network for semantic segmentation and object recognition with 3D point clouds. At the core of our network is point-wise convolution, a new convolution operator that can be applied at each point of a point cloud. Our fully convolutional network design, while being surprisingly simple to implement, can yield competitive accuracy in both semantic segmentation and object recognition task.
ISSN:2575-7075
DOI:10.1109/CVPR.2018.00109