论文标题
本地地区学习网络：有意义的地方区域，用于有效的点云分析
Local-Area-Learning Network: Meaningful Local Areas for Efficient Point Cloud Analysis
论文作者
论文摘要
近年来，通过深层神经网络进行了积分云分析的研究取得了迅速的进展。开创性的工作角网提供了对点云的直接分析。但是，由于其体系结构，点网无法捕获本地结构。为了克服这一缺点，同一位作者通过将PointNet应用于局部区域开发了PointNet ++。当地地区由中心点及其邻居定义。在PointNet ++及其进一步的发展中，中心点由最远的点采样（FPS）算法确定。这是一个缺点，即中心的点一般没有有意义的地方区域。在本文中，我们介绍了神经本地地区学习网络（本地网络），该网络强调了当地的选择和表征。我们的方法学习了我们用作中心点的关键要点。为了加强对局部结构的识别，根据当地区域，给出了额外的度量特性。最后，我们得出并结合了两个全球特征向量，一个来自整个点云，一个来自所有当地区域。数据集ModelNet10/40和Shapenet上的实验表明，局部网络对零件分割具有竞争力。对于分类，本地网络的表现优于最先进的。
Research in point cloud analysis with deep neural networks has made rapid progress in recent years. The pioneering work PointNet offered a direct analysis of point clouds. However, due to its architecture PointNet is not able to capture local structures. To overcome this drawback, the same authors have developed PointNet++ by applying PointNet to local areas. The local areas are defined by center points and their neighbors. In PointNet++ and its further developments the center points are determined with a Farthest Point Sampling (FPS) algorithm. This has the disadvantage that the center points in general do not have meaningful local areas. In this paper, we introduce the neural Local-Area-Learning Network (LocAL-Net) which places emphasis on the selection and characterization of the local areas. Our approach learns critical points that we use as center points. In order to strengthen the recognition of local structures, the points are given additional metric properties depending on the local areas. Finally, we derive and combine two global feature vectors, one from the whole point cloud and one from all local areas. Experiments on the datasets ModelNet10/40 and ShapeNet show that LocAL-Net is competitive for part segmentation. For classification LocAL-Net outperforms the state-of-the-arts.
