ChartPointFlow for Topology-Aware 3D Point Cloud Generation
ChartPointFlow for Topology-Aware 3D Point Cloud Generation
复制标题
DOI：
10.1145/3474085.3475589
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Takumi Kimura;Takashi Matsubara;K. Uehara
中科院分区：
文献类型：
--
作者：
Takumi Kimura;Takashi Matsubara;K. Uehara
点云作为三维（3D）形状表面的表示。深度生成模型已经被用来模拟它们的变化，通常使用来自一组球状潜在变量的地图。然而，以往的方法并没有很好地关注点云的拓扑结构，尽管一个连续的图不能表达不同数量的孔和交集。此外，点云通常由多个子部分组成，也难以表达。在这项研究中，我们提出了ChartPointFlow，一个基于流的生成模型，具有多个潜在标签的3D点云。每个标签以无监督的方式分配给点。然后，将以标签为条件的映射分配给点云的连续子集，类似于流形的图。这使得我们提出的模型能够保持具有清晰边界的拓扑结构，而以前的方法往往会产生模糊的点云并且无法产生孔。实验结果表明，与其他点云生成器相比，ChartPointFlow在生成和重建方面达到了最先进的性能。此外，ChartPointFlow使用图表将对象划分为语义子部分，并且在无监督分割的情况下表现出优越的性能。
A point cloud serves as a representation of the surface of a three-dimensional (3D) shape. Deep generative models have been adapted to model their variations typically using a map from a ball-like set of latent variables. However, previous approaches did not pay much attention to the topological structure of a point cloud, despite that a continuous map cannot express the varying numbers of holes and intersections. Moreover, a point cloud is often composed of multiple subparts, and it is also difficult to express. In this study, we propose ChartPointFlow, a flow-based generative model with multiple latent labels for 3D point clouds. Each label is assigned to points in an unsupervised manner. Then, a map conditioned on a label is assigned to a continuous subset of a point cloud, similar to a chart of a manifold. This enables our proposed model to preserve the topological structure with clear boundaries, whereas previous approaches tend to generate blurry point clouds and fail to generate holes. The experimental results demonstrate that ChartPointFlow achieves state-of-the-art performance in terms of generation and reconstruction compared with other point cloud generators. Moreover, ChartPointFlow divides an object into semantic subparts using charts, and it demonstrates superior performance in case of unsupervised segmentation.