论文标题
Tearingnet：Point Cloud AutoCododer学习拓扑友好的表示
TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations
论文作者
论文摘要
拓扑很重要。尽管点云处理和几何深度学习最近取得了成功，但使用学习模型捕获点云数据的复杂拓扑仍然很艰巨。给定一个点云数据集，该数据集包含具有各种属或具有多个对象的场景的对象，我们建议使用固定长度描述符来代表点云的具有挑战性的任务。与现有的作品直接变形了零属（例如，2平方贴片）的预定义的原始基因与对象级点云相比，我们的TearingNet的特征是提出的撕裂网络模块和折叠网络模块相互迭代相互作用。特别是，撕裂网络模块明确学习了点云拓扑。通过打破原始图的边缘，它将图表撕成斑块或孔中以模拟目标点云的拓扑，从而导致忠实的重建。实验表明，在重建点云方面，我们的提议的优越性以及比基准比基准更具拓扑友好的表示。
Topology matters. Despite the recent success of point cloud processing with geometric deep learning, it remains arduous to capture the complex topologies of point cloud data with a learning model. Given a point cloud dataset containing objects with various genera, or scenes with multiple objects, we propose an autoencoder, TearingNet, which tackles the challenging task of representing the point clouds using a fixed-length descriptor. Unlike existing works directly deforming predefined primitives of genus zero (e.g., a 2D square patch) to an object-level point cloud, our TearingNet is characterized by a proposed Tearing network module and a Folding network module interacting with each other iteratively. Particularly, the Tearing network module learns the point cloud topology explicitly. By breaking the edges of a primitive graph, it tears the graph into patches or with holes to emulate the topology of a target point cloud, leading to faithful reconstructions. Experimentation shows the superiority of our proposal in terms of reconstructing point clouds as well as generating more topology-friendly representations than benchmarks.
