论文标题
通过双曲线空间中的正则化重新考虑点云的组成性
Rethinking the compositionality of point clouds through regularization in the hyperbolic space
论文作者
论文摘要
3D对象的点云具有固有的组成性质，可以将简单的部分组装成逐渐复杂的形状以形成整个对象。明确地捕获这种部分整体层次结构是一个长期的目标，以建立有效的模型，但其树木般的性质使这项任务难以捉摸。在本文中，我们建议将点云分类器的特征嵌入双曲线空间中，并明确规范空间以说明零件整体层次结构。双曲线空间是唯一可以成功嵌入层次结构的树状性质的空间。这导致了对点云分类的最新监督模型的性能的实质性改善。
Point clouds of 3D objects exhibit an inherent compositional nature where simple parts can be assembled into progressively more complex shapes to form whole objects. Explicitly capturing such part-whole hierarchy is a long-sought objective in order to build effective models, but its tree-like nature has made the task elusive. In this paper, we propose to embed the features of a point cloud classifier into the hyperbolic space and explicitly regularize the space to account for the part-whole hierarchy. The hyperbolic space is the only space that can successfully embed the tree-like nature of the hierarchy. This leads to substantial improvements in the performance of state-of-art supervised models for point cloud classification.
