Pointwise Convolutional Neural Networks

Binh-Son Hua1,2         Minh-Khoi Tran1          Sai-Kit Yeung1

1Singapore University of Technology and Design 2The University of Tokyo

Point-wise convolution

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.

Code (releasing soon, tidying up in progress)

    title = {Pointwise Convolutional Neural Networks},
    author = {Binh-Son Hua and Minh-Khoi Tran and Sai-Kit Yeung},
    conference = {Computer Vision and Pattern Recognition (CVPR)},
    year = {2018}


This work was done during Binh-Son Hua was a postdoctoral researcher in Singapore University of Technology and Design.

Sai-Kit Yeung is supported by Singapore MOE Academic Research Fund MOE2013-T2-1-159 and SUTD-MIT International Design Center Grant IDG31300106. We acknowledge the support of the SUTD Digital Manufacturing and Design (DManD) Centre which is supported by the National Research Foundation (NRF) of Singapore. This research is also supported by the National Research Foundation, Prime Minister's Office, Singapore under its IDM Futures Funding Initiative.