SOTAVerified

Pointwise Convolutional Neural Networks

2017-12-14CVPR 2018Code Available0· sign in to hype

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

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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 pointwise 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.

Tasks

Reproductions