论文标题
SoftpoolNet：用于点云完成和分类的形状描述符
SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
论文作者
论文摘要
点云通常是许多应用程序的默认选择，因为它们表现出比体积数据更高的灵活性和效率。然而，他们无组织的性质 - 以无序的方式存储 - 使它们不适合通过深度学习管道处理。在本文中，我们提出了一种基于点云的3D对象完成和分类的方法。我们介绍了一种基于其激活组织的新方法来组织提取的功能，我们将其命名为软池。对于解码器阶段，我们提出了区域卷积，这是一个旨在最大化全球激活熵的新型操作员。此外，受到点完成网络（PCN）的本地精炼过程的启发，我们还提出了一个拟定的操作，以模拟点云的反向解决操作。本文证明，我们的区域激活可以纳入Atlasnet和PCN等许多点云体系结构中，从而为几何完成提供了更好的性能。我们在不同的3D任务（例如对象完成和分类）上评估我们的方法，从而实现最新的准确性。
Point clouds are often the default choice for many applications as they exhibit more flexibility and efficiency than volumetric data. Nevertheless, their unorganized nature -- points are stored in an unordered way -- makes them less suited to be processed by deep learning pipelines. In this paper, we propose a method for 3D object completion and classification based on point clouds. We introduce a new way of organizing the extracted features based on their activations, which we name soft pooling. For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy. Furthermore, inspired by the local refining procedure in Point Completion Network (PCN), we also propose a patch-deforming operation to simulate deconvolutional operations for point clouds. This paper proves that our regional activation can be incorporated in many point cloud architectures like AtlasNet and PCN, leading to better performance for geometric completion. We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
