Point Cloud Processing via Recurrent Set Encoding
Point Cloud Processing via Recurrent Set Encoding
复制标题
DOI：
10.1609/aaai.v33i01.33015441
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Pengxiang Wu;Chao Chen;Jingru Yi;Dimitris N. Metaxas
中科院分区：
文献类型：
--
作者：
Pengxiang Wu;Chao Chen;Jingru Yi;Dimitris N. Metaxas
提出了一种新的用于三维点云处理的置换不变网络。我们的网络由一个递归集编码器和一个卷积特征聚合器组成。给定一个无序点集，编码器首先将其周围空间划分为平行光束。然后，每个波束内的点被建模为一个序列，并通过共享的递归神经网络（RNN）编码成次区域几何特征。波束的空间布局是规则的，这允许波束特征被进一步馈送到有效的2D卷积神经网络（CNN）中，用于分层特征聚合。我们的网络在空间特征学习方面是有效的，并且在许多基准测试中与最先进的（SOTA）竞争。与此同时，与SOTA相比，它的效率更高。
We present a new permutation-invariant network for 3D point cloud processing. Our network is composed of a recurrent set encoder and a convolutional feature aggregator. Given an unordered point set, the encoder firstly partitions its ambient space into parallel beams. Points within each beam are then modeled as a sequence and encoded into subregional geometric features by a shared recurrent neural network (RNN). The spatial layout of the beams is regular, and this allows the beam features to be further fed into an efficient 2D convolutional neural network (CNN) for hierarchical feature aggregation. Our network is effective at spatial feature learning, and competes favorably with the state-of-the-arts (SOTAs) on a number of benchmarks. Meanwhile, it is significantly more efficient compared to the SOTAs.