Abstract
We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds. The network architecture capitalizes on the sparse nature of irregular point
clouds, and hierarchically coarsens the data representation
with space partitioning. At the same time, the proposed
spherical kernels systematically quantize point neighborhoods to identify local geometric structures in the data,
while maintaining the properties of translation-invariance
and asymmetry. We specify spherical kernels with the help
of network neurons that in turn are associated with spatial locations. We exploit this association to avert dynamic
kernel generation during network training that enables ef-
ficient learning with high resolution point clouds. The effectiveness of the proposed technique is established on the
benchmark tasks of 3D object classification and segmentation, achieving competetive performance on ShapeNet and
RueMonge2014 datasets.