Concentric Spherical GNN for 3D Representation Learning

James S Fox, Bo Zhao, Sivasankaran Rajamanickam, Rampi Ramprasad, Le Song

Keywords: spherical cnn, GNN, graph convolution, rotation equivariance, 3D

Abstract:

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 using radial basis functions, thereby bridging spherical convolutions on grids with general point clouds.
We demonstrate the effectiveness of our approach in achieving state-of-the-art performance on 3D classification tasks with rotated data.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose a spherical GNN based on concentric spheres representation for 3D representation learning.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=cGP6ecJWpt