Multi-directional Geodesic Neural Networks via Equivariant Convolution

10/01/2018
by   Adrien Poulenard, et al.
0

We propose a novel approach for performing convolution of signals on curved surfaces and show its utility in a variety of geometric deep learning applications. Key to our construction is the notion of directional functions defined on the surface, which extend the classic real-valued signals and which can be naturally convolved with with real-valued template functions. As a result, rather than trying to fix a canonical orientation or only keeping the maximal response across all alignments of a 2D template at every point of the surface, as done in previous works, we show how information across all rotations can be kept across different layers of the neural network. Our construction, which we call multi-directional geodesic convolution, or directional convolution for short, allows, in particular, to propagate and relate directional information across layers and thus different regions on the shape. We first define directional convolution in the continuous setting, prove its key properties and then show how it can be implemented in practice, for shapes represented as triangle meshes. We evaluate directional convolution in a wide variety of learning scenarios ranging from classification of signals on surfaces, to shape segmentation and shape matching, where we show a significant improvement over several baselines.

READ FULL TEXT
research
05/26/2020

CNNs on Surfaces using Rotation-Equivariant Features

This paper is concerned with a fundamental problem in geometric deep lea...
research
12/01/2020

DiffusionNet: Discretization Agnostic Learning on Surfaces

We introduce a new approach to deep learning on 3D surfaces, based on th...
research
06/11/2018

Latent Space Representation for Shape Analysis and Learning

We propose a novel shape representation useful for analyzing and process...
research
07/01/2019

Learning to Approximate Directional Fields Defined over 2D Planes

Reconstruction of directional fields is a need in many geometry processi...
research
11/30/2018

TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes

We introduce, TextureNet, a neural network architecture designed to extr...
research
08/15/2018

Convolutional Neural Networks on 3D Surfaces Using Parallel Frames

We extend Convolutional Neural Networks (CNNs) on flat and regular domai...
research
03/25/2018

P2P-NET: Bidirectional Point Displacement Net for Shape Transform

We introduce P2P-NET, a general-purpose deep neural network which learns...

Please sign up or login with your details

Forgot password? Click here to reset