Spherical Convolutional Neural Network for 3D Point Clouds

Abstract

We propose a neural network for 3D point cloud processing that exploits `spherical' convolution kernels and octree partitioning of space. The proposed metric-based spherical kernels systematically quantize point neighborhoods to identify local geometric structures in data, while maintaining the properties of translation-invariance and asymmetry. The network architecture itself is guided by octree data structuring that takes full advantage of the sparse nature of irregular point clouds. We specify spherical kernels with the help of neurons in each layer that in turn are associated with spatial locations. We exploit this association to avert dynamic kernel generation during network training, that enables efficient learning with high resolution point clouds. We demonstrate the utility of the spherical convolutional neural network for 3D object classification on standard benchmark datasets.

arXiv commentSubmitted to a conference

References in corpus (1)

• FPNN: Field Probing Neural Networks for 3D Data

Cited by in corpus (6)

• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
• Deep Learning for 3D Point Clouds: A Survey
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review
• Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoders
• Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds
• Irregular Convolutional Auto-Encoder on Point Clouds