arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.12663cs.CV
收藏

基于点注意力网络的三维点云语义分割

Point Attention Network for Semantic Segmentation of 3D Point Clouds

Hunan University(湖南大学);Xidian University(西安电子科技大学);Hunan Agricultural University(湖南农业大学);The University of Western Australia(西澳大利亚大学)

Mingtao Feng, Liang Zhang, Xuefei Lin, Syed Zulqarnain Gilani, Ajmal Mian

摘要:

卷积神经网络(CNN)在由规则排列的网格(如图像)表示的数据上表现得非常好。然而,由于稀疏3D点云的不规则和无序性质,直接利用经典卷积核或参数共享机制是低效的。我们提出了一个点注意力网络,学习丰富的局部形状特征及其上下文相关性的三维点云语义分割。由于相邻点的几何分布是不变的点排序,我们提出了一个局部注意力边缘卷积(LAE Conv)构建一个局部图的基础上搜索的邻域点在多个方向上。我们分配注意力系数到每个边缘,然后聚合点特征作为其邻居的加权和。然后,将学习到的LAE-Conv层特征提供给逐点空间注意力模块,以生成所有点的相互依赖矩阵,而不管它们的距离如何,该矩阵捕获有助于更精确语义信息的长距离空间上下文特征。所提出的点注意力网络由编码器和解码器组成,再加上LAE-Conv层和逐点空间注意力模块,使其成为一个端到端的可训练网络,用于预测3D点云分割的密集标签。在具有挑战性的3D点云基准上的实验表明,我们的算法可以达到或优于现有的最先进的方法。

英文摘要:

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D point clouds is inefficient due to their irregular and unordered nature. We propose a point attention network that learns rich local shape features and their contextual correlations for 3D point cloud semantic segmentation. Since the geometric distribution of the neighboring points is invariant to the point ordering, we propose a Local Attention-Edge Convolution (LAE Conv) to construct a local graph based on the neighborhood points searched in multi-directions. We assign attention coefficients to each edge and then aggregate the point features as a weighted sum of its neighbors. The learned LAE-Conv layer features are then given to a point-wise spatial attention module to generate an interdependency matrix of all points regardless of their distances, which captures long-range spatial contextual features contributing to more precise semantic information. The proposed point attention network consists of an encoder and decoder which, together with the LAE-Conv layers and the point-wise spatial attention modules, make it an end-to-end trainable network for predicting dense labels for 3D point cloud segmentation. Experiments on challenging benchmarks of 3D point clouds show that our algorithm can perform at par or better than the existing state of the art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑