Octree guided CNN with Spherical Kernels for 3D Point Clouds
This work addresses the challenge of processing irregular 3D point clouds for computer vision applications, representing an incremental improvement over existing methods.
The authors tackled the problem of machine learning from arbitrary 3D point clouds by proposing an octree guided neural network with spherical kernels, achieving new state-of-the-art results on 3D object classification and segmentation tasks on ShapeNet and RueMonge2014 datasets.
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 efficient 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 new state-of-the-art on ShapeNet and RueMonge2014 datasets.