MeshWalker：基于随机游动的网格深度理解
MeshWalker: Deep Mesh Understanding by Random Walks
摘要：
大多数为深度学习表示3D形状的尝试都集中在体积网格、多视图图像和点云上。在本文中，我们研究了计算机图形学中最流行的3D形状表示-三角形网格-并询问如何在深度学习中使用它。回答这个问题的少数尝试提出调整卷积和池化以适应卷积神经网络（CNN）。本文提出了一种非常不同的方法，称为MeshWalker，直接从给定的网格中学习形状。其关键思想是通过沿表面的随机行走来表示网格，这将“探索”网格的几何和拓扑。每次行走都被组织为顶点列表，这以某种方式对网格施加规则性。步行被输入到一个递归神经网络（RNN）中，该网络“记住”步行的历史。我们表明，我们的方法实现了两个基本的形状分析任务的最先进的结果：形状分类和语义分割。此外，即使是非常少量的例子也足以用于学习。这是非常重要的，因为很难获得大的网格数据集。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
