Concentric Spherical GNN for 3D Representation Learning

by   James Fox, et al.

Learning 3D representations that generalize well to arbitrarily oriented inputs is a challenge of practical importance in applications varying from computer vision to physics and chemistry. We propose a novel multi-resolution convolutional architecture for learning over concentric spherical feature maps, of which the single sphere representation is a special case. Our hierarchical architecture is based on alternatively learning to incorporate both intra-sphere and inter-sphere information. We show the applicability of our method for two different types of 3D inputs, mesh objects, which can be regularly sampled, and point clouds, which are irregularly distributed. We also propose an efficient mapping of point clouds to concentric spherical images, thereby bridging spherical convolutions on grids with general point clouds. We demonstrate the effectiveness of our approach in improving state-of-the-art performance on 3D classification tasks with rotated data.



There are no comments yet.


page 6

page 8


Octree guided CNN with Spherical Kernels for 3D Point Clouds

We propose an octree guided neural network architecture and spherical co...

Spherical Conformal Parameterization of Genus-0 Point Clouds for Meshing

Point cloud is the most fundamental representation of 3D geometric objec...

Spherical Convolutional Neural Network for 3D Point Clouds

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

Learning to Orient Surfaces by Self-supervised Spherical CNNs

Defining and reliably finding a canonical orientation for 3D surfaces is...

SN-Graph: a Minimalist 3D Object Representation for Classification

Using deep learning techniques to process 3D objects has achieved many s...

Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods

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

Generating Large Convex Polytopes Directly on Point Clouds

In this paper, we present a method to efficiently generate large, free, ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.