PointCNN: Convolution On X-Transformed Points
PointCNN: Convolution On X-Transformed Points
复制标题
DOI：
--
复制
发表时间：
2018-01
期刊：
影响因子：
--
通讯作者：
Yangyan Li;Rui Bu;Mingchao Sun;Wei Wu;Xinhan Di;Baoquan Chen
中科院分区：
文献类型：
--
作者：
Yangyan Li;Rui Bu;Mingchao Sun;Wei Wu;Xinhan Di;Baoquan Chen
我们提出了一个简单而通用的框架，从点云特征学习。CNN成功的关键是卷积运算符，它能够利用网格（例如图像）中密集表示的数据的空间局部相关性。然而，点云是不规则的和无序的，因此直接卷积核与点相关联的特征，将导致形状信息和方差点排序的遗弃。为了解决这些问题，我们建议从输入点学习$\mathcal{X}$-转换，以同时促进两个原因。第一个是与点相关联的输入特征的加权，第二个是将点排列成潜在的和潜在的规范顺序。典型卷积算子的元素乘积和求和运算随后应用于$\mathcal{X}$变换特征。该方法是典型CNN从点云特征学习的推广，因此我们称之为PointCNN。实验表明，PointCNN在多个具有挑战性的基准数据集和任务上实现了与最先进的方法相当或更好的性能。
We present a simple and general framework for feature learning from point clouds. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images). However, point clouds are irregular and unordered, thus directly convolving kernels against features associated with the points, will result in desertion of shape information and variance to point ordering. To address these problems, we propose to learn an $\mathcal{X}$-transformation from the input points, to simultaneously promote two causes. The first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Element-wise product and sum operations of the typical convolution operator are subsequently applied on the $\mathcal{X}$-transformed features. The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN. Experiments show that PointCNN achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets and tasks.