DeepAI AI Chat
Log In Sign Up

MeshWalker: Deep Mesh Understanding by Random Walks

by   Alon Lahav, et al.

Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a triangular mesh - and ask how it can be utilized within deep learning. The few attempts to answer this question propose to adapt convolutions pooling to suit Convolutional Neural Networks (CNNs). This paper proposes a very different approach, termed MeshWalker, to learn the shape directly from a given mesh. The key idea is to represent the mesh by random walks along the surface, which "explore" the mesh's geometry and topology. Each walk is organized as a list of vertices, which in some manner imposes regularity on the mesh. The walk is fed into a Recurrent Neural Network (RNN) that "remembers" the history of the walk. We show that our approach achieves state-of-the-art results for two fundamental shape analysis tasks: shape classification and semantic segmentation. Furthermore, even a very small number of examples suffices for learning. This is highly important, since large datasets of meshes are difficult to acquire.


page 1

page 3

page 7

page 8

page 9


CloudWalker: 3D Point Cloud Learning by Random Walks for Shape Analysis

Point clouds are gaining prominence as a method for representing 3D shap...

AttWalk: Attentive Cross-Walks for Deep Mesh Analysis

Mesh representation by random walks has been shown to benefit deep learn...

Random Walks for Adversarial Meshes

A polygonal mesh is the most-commonly used representation of surfaces in...

A Review of Deep Learning-Powered Mesh Reconstruction Methods

With the recent advances in hardware and rendering techniques, 3D models...

Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation

Generative models for 3D geometric data arise in many important applicat...

3D Shape Segmentation with Geometric Deep Learning

The semantic segmentation of 3D shapes with a high-density of vertices c...

PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

3D shape representation and its processing have substantial effects on 3...