DiffusionNet: Discretization Agnostic Learning on Surfaces

12/01/2020
by   Nicholas Sharp, et al.
66

We introduce a new approach to deep learning on 3D surfaces, based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks automatically generalize across different samplings and resolutions of a surface – a basic property which is crucial for practical applications. Our networks can be discretized on various geometric representations such as triangle meshes or point clouds, and can even be trained on one representation then applied to another. We optimize the spatial support of diffusion as a continuous network parameter ranging from purely local to totally global, removing the burden of manually choosing neighborhood sizes. The only other ingredients in the method are a multi-layer perceptron applied independently at each point, and spatial gradient features to support directional filters. The resulting networks are simple, robust, and efficient. Here, we focus primarily on triangle mesh surfaces, and demonstrate state-of-the-art results for a variety of tasks including surface classification, segmentation, and non-rigid correspondence.

READ FULL TEXT

page 1

page 5

page 7

page 14

page 16

research
05/26/2020

CNNs on Surfaces using Rotation-Equivariant Features

This paper is concerned with a fundamental problem in geometric deep lea...
research
07/10/2023

A Fast Geometric Multigrid Method for Curved Surfaces

We introduce a geometric multigrid method for solving linear systems ari...
research
10/01/2018

Multi-directional Geodesic Neural Networks via Equivariant Convolution

We propose a novel approach for performing convolution of signals on cur...
research
01/23/2023

CircNet: Meshing 3D Point Clouds with Circumcenter Detection

Reconstructing 3D point clouds into triangle meshes is a key problem in ...
research
09/15/2023

Large Intestine 3D Shape Refinement Using Point Diffusion Models for Digital Phantom Generation

Accurate 3D modeling of human organs plays a crucial role in building co...
research
03/21/2021

ActivationNet: Representation learning to predict contact quality of interacting 3-D surfaces in engineering designs

Engineering simulations for analysis of structural and fluid systems req...
research
07/04/2021

Repulsive Surfaces

Functionals that penalize bending or stretching of a surface play a key ...

Please sign up or login with your details

Forgot password? Click here to reset