Deep learning

Point cloud

Pattern recognition (psychology)

Mathematics

Convolution (computer science)

Cognitive neuroscience of visual object recognition

Mathematical analysis

Artificial intelligence

Management

Economics

Pointwise

Computer science

Task (project management)

Object (grammar)

Artificial neural network

Convolutional neural network

Segmentation

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.

Pointwise Convolutional Neural Networks