arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09228cs.CV
收藏

用于点云分析的双邻域深度融合网络

Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis

National University of Defense Technology(中国人民解放军国防科技大学);University of Science and Technology of China(中国科学技术大学)

Guoquan Xu, Hezhi Cao, Yifan Zhang, Jianwei Wan, Ke Xu, Yanxin Ma

摘要:

最近,深度神经网络在三维点云分类方面取得了显著的成就。然而,现有的分类方法主要是在理想化的点云上实现的,并且在非理想化的情况下遭受严重的性能退化。针对这一问题,提出了一种特征表示学习方法--双邻域深度融合网络(DNDFN),作为一种改进的点云编码器,用于非理想化点云分类。DNDFN利用一种称为TN学习的可训练邻域学习方法来捕获全局关键邻域。然后,融合全局邻域和局部邻域,使网络具有更强的推理能力。此外,提出了一种信息传递卷积(IT-Conv)算法,用于DNDFN学习点对之间的边缘信息,有利于特征传递过程。信息在IT-Conv中的传递类似于信息在图中的传播,这使得DNDFN更接近人类的推理模式。在已有的基准测试特别是非理想数据集上的大量实验验证了DNDFN的有效性,DNDFN达到了最新的水平。

英文摘要:

Recently, deep neural networks have made remarkable achievements in 3D point cloud classification. However, existing classification methods are mainly implemented on idealized point clouds and suffer heavy degradation of per-formance on non-idealized scenarios. To handle this prob-lem, a feature representation learning method, named Dual-Neighborhood Deep Fusion Network (DNDFN), is proposed to serve as an improved point cloud encoder for the task of non-idealized point cloud classification. DNDFN utilizes a trainable neighborhood learning method called TN-Learning to capture the global key neighborhood. Then, the global neighborhood is fused with the local neighbor-hood to help the network achieve more powerful reasoning ability. Besides, an Information Transfer Convolution (IT-Conv) is proposed for DNDFN to learn the edge infor-mation between point-pairs and benefits the feature transfer procedure. The transmission of information in IT-Conv is similar to the propagation of information in the graph which makes DNDFN closer to the human reasoning mode. Extensive experiments on existing benchmarks especially non-idealized datasets verify the effectiveness of DNDFN and DNDFN achieves the state of the arts.

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。

↑