Point clouds are gaining prominence as a method for representing 3D shapes, but their irregular structure poses a challenge for deep learning methods. In this paper we propose CloudWalker, a novel method for learning 3D shapes using random walks. Previous works attempt to adapt Convolutional Neural Networks (CNNs) or impose a grid or mesh structure to 3D point clouds. This work presents a different approach for representing and learning the shape from a given point set. The key idea is to impose structure on the point set by multiple random walks through the cloud for exploring different regions of the 3D object. Then we learn a per-point and per-walk representation and aggregate multiple walk predictions at inference. Our approach achieves state-of-the-art results for two 3D shape analysis tasks: classification and retrieval.
翻译:点云作为代表 3D 形状的一种方法越来越显眼, 但是它们的非常规结构对深层学习方法构成挑战。 在本文中, 我们提出云华克( CloudWalker ), 这是使用随机行走来学习 3D 形状的一种新颖方法 。 以前的工作试图调整进化神经网络( CNNs ), 或者将网格或网格结构强制到 3D 点云 。 这项工作为代表并学习 3D 形状设定的形状提供了不同的方法 。 关键的想法是将结构强加在由多个随机行走的云上, 以探索 3D 对象的不同区域 。 然后我们学习了 per 点 和 单行代表 和 综合 多重行走预测 。 我们的方法为两个 3D 形状分析任务( 分类和 检索) 取得了最先进的结果 。