论文标题
复合卷积：3D点云上深度学习的灵活操作员
Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Clouds
论文作者
论文摘要
深度神经网络需要特定的层来处理点云，因为3D点的散射和不规则位置阻止了常规卷积过滤器的使用。我们介绍了复合层，这是处理3D点云的现有卷积运算符的灵活替代方案。我们设计复合层以从点的3D坐标提取和压缩空间信息，然后将其与特征向量相结合。与主流点跨义层（例如Dockpoint和KPCONV）相比，我们的复合层保证了网络设计中的灵活性更大，并提供了另一种正则化形式。为了证明我们的复合层的通用性，我们既定义了卷积复合层，又定义了以非线性方式组合空间信息和特征的聚合版本，并且我们使用这些层来实现CompositeNets。我们对合成和现实世界数据集的实验表明，在分类，分割和异常检测中，我们的CompoSitenets均优于使用相同的顺序体系结构，并获得了与KPCONV相似的结果，该结果具有更深的残基体系结构。此外，我们的综合材料在点云上的异常检测中实现了最先进的性能。我们的代码可在\ url {https://github.com/sirolf-otrebla/compositenet}上公开获得。
Deep neural networks require specific layers to process point clouds, as the scattered and irregular location of 3D points prevents the use of conventional convolutional filters. We introduce the composite layer, a flexible and general alternative to the existing convolutional operators that process 3D point clouds. We design our composite layer to extract and compress the spatial information from the 3D coordinates of points and then combine this with the feature vectors. Compared to mainstream point-convolutional layers such as ConvPoint and KPConv, our composite layer guarantees greater flexibility in network design and provides an additional form of regularization. To demonstrate the generality of our composite layers, we define both a convolutional composite layer and an aggregate version that combines spatial information and features in a nonlinear manner, and we use these layers to implement CompositeNets. Our experiments on synthetic and real-world datasets show that, in both classification, segmentation, and anomaly detection, our CompositeNets outperform ConvPoint, which uses the same sequential architecture, and achieve similar results as KPConv, which has a deeper, residual architecture. Moreover, our CompositeNets achieve state-of-the-art performance in anomaly detection on point clouds. Our code is publicly available at \url{https://github.com/sirolf-otrebla/CompositeNet}.
