Primal-Dual Mesh Convolutional Neural Networks

by   Francesco Milano, et al.

Recent works in geometric deep learning have introduced neural networks that allow performing inference tasks on three-dimensional geometric data by defining convolution, and sometimes pooling, operations on triangle meshes. These methods, however, either consider the input mesh as a graph, and do not exploit specific geometric properties of meshes for feature aggregation and downsampling, or are specialized for meshes, but rely on a rigid definition of convolution that does not properly capture the local topology of the mesh. We propose a method that combines the advantages of both types of approaches, while addressing their limitations: we extend a primal-dual framework drawn from the graph-neural-network literature to triangle meshes, and define convolutions on two types of graphs constructed from an input mesh. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them using an attention mechanism. At the same time, we introduce a pooling operation with a precise geometric interpretation, that allows handling variations in the mesh connectivity by clustering mesh faces in a task-driven fashion. We provide theoretical insights of our approach using tools from the mesh-simplification literature. In addition, we validate experimentally our method in the tasks of shape classification and shape segmentation, where we obtain comparable or superior performance to the state of the art.


page 8

page 9

page 18


Laplacian2Mesh: Laplacian-Based Mesh Understanding

Geometric deep learning has sparked a rising interest in computer graphi...

DualConv: Dual Mesh Convolutional Networks for Shape Correspondence

Convolutional neural networks have been extremely successful for 2D imag...

Geometric Feature Learning for 3D Meshes

Geometric feature learning for 3D meshes is central to computer graphics...

Picasso: A CUDA-based Library for Deep Learning over 3D Meshes

We present Picasso, a CUDA-based library comprising novel modules for de...

Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs

A common approach to define convolutions on meshes is to interpret them ...

Adaptive Mesh Booleans

We present a new method for performing Boolean operations on volumes rep...

MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation

Mesh-based learning is one of the popular approaches nowadays to learn s...