arXiv Analytics

Sign in

arXiv:1712.05245 [cs.CV]AbstractReferencesReviewsResources

Point-wise Convolutional Neural Network

Binh-Son Hua, Minh-Khoi Tran, Sai-Kit Yeung

Published 2017-12-14Version 1

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 technical report, 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 convolution operator that can be applied at each point of a point cloud. Our fully convolutional network design, while being simple to implement, can yield competitive accuracy in both semantic segmentation and object recognition task.

Related articles: Most relevant | Search more
arXiv:1710.07563 [cs.CV] (Published 2017-10-20)
SEGCloud: Semantic Segmentation of 3D Point Clouds
arXiv:1703.07684 [cs.CV] (Published 2017-03-22)
Predicting Deeper into the Future of Semantic Segmentation
arXiv:1707.02392 [cs.CV] (Published 2017-07-08)
Representation Learning and Adversarial Generation of 3D Point Clouds