MeshCNN: A Network with an Edge

TL;DR

MeshCNN introduces a neural network architecture that directly analyzes 3D triangular meshes by operating on mesh edges, utilizing specialized convolution and pooling layers to effectively capture shape features.

Contribution

This paper presents MeshCNN, a novel neural network designed specifically for triangular meshes, with edge-based convolution and pooling operations that preserve topology and improve shape analysis.

Findings

Effective on various 3D shape tasks

Preserves surface topology during pooling

Learns to identify important mesh edges

Abstract

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networks that combine convolution and pooling operations. In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes. Analogous to classic CNNs, MeshCNN combines specialized convolution and pooling layers that operate on the mesh edges, by leveraging their intrinsic geodesic connections. Convolutions are applied on edges and the four edges of their incident triangles, and pooling is applied via an edge collapse operation that retains surface topology, thereby, generating new mesh connectivity for the subsequent convolutions. MeshCNN learns which edges to collapse, thus forming a task-driven process where the network exposes and expands the important features while discarding the redundant ones. We demonstrate the effectiveness of our task-driven pooling on various learning tasks applied to 3D meshes.