DeepAI AI Chat
Log In Sign Up

Octree guided CNN with Spherical Kernels for 3D Point Clouds

by   Huan Lei, et al.
The University of Western Australia

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.


Spherical Convolutional Neural Network for 3D Point Clouds

We propose a neural network for 3D point cloud processing that exploits ...

Concentric Spherical GNN for 3D Representation Learning

Learning 3D representations that generalize well to arbitrarily oriented...

Efficient Learning on Point Clouds with Basis Point Sets

With the increased availability of 3D scanning technology, point clouds ...

Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods

This paper introduces a new definition of multiscale neighborhoods in 3D...

Multi-Kernel Diffusion CNNs for Graph-Based Learning on Point Clouds

Graph convolutional networks are a new promising learning approach to de...

PCEDNet : A Neural Network for Fast and Efficient Edge Detection in 3D Point Clouds

In recent years, Convolutional Neural Networks (CNN) have proven to be e...

Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme

While object semantic understanding is essential for most service roboti...

Code Repositories



view repo