Abstract
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.
Original language | English |
---|---|
Article number | 263 |
Journal | ACM Transactions on Graphics |
Volume | 39 |
Issue number | 6 |
DOIs | |
State | Published - 26 Nov 2020 |
Keywords
- deep learning
- random walks
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design