Cosmos Propagation Network: Deep learning model for point cloud completion
Cosmos Propagation Network: Deep learning model for point cloud completion
复制标题
DOI：
10.1016/j.neucom.2022.08.007
复制
发表时间：
2022-08
期刊：
影响因子：
6
通讯作者：
Fangzhou Lin;Yajun Xu;Ziming Zhang;Chenyang Gao;Kazunori D. Yamada
中科院分区：
文献类型：
--
作者：
Fangzhou Lin;Yajun Xu;Ziming Zhang;Chenyang Gao;Kazunori D. Yamada
由3D扫描设备测量的点云通常由于扫描仪的视图定位而具有部分缺失的数据。缺失的数据会降低点云在下游任务（如分割、定位和姿态估计）中的性能。因此，3D点云完成旨在预测这些基本3D视觉任务的不完整对象的缺失区域。然而，预测完整的对象可以很容易地减少测量区域的细节或结构，这通常不需要修复。本研究提出一种新颖的神经网络架构，宇宙传播网络（CP-Net），三维点云完成。CP-Net从作为输入的不完整点云中提取不同尺度的潜在特征。对于点云生成，我们提出了一种新的使用Mirror Expand模块的点扩展方法。与现有的方法相比，镜像扩展模块引入了较少的信息冗余，使得点的分布更加可靠。CP-Net预测缺失区域的细节，并保持清晰的总体结构。CP-Net在几个基准上的性能与目前的基线方法进行了比较。与现有方法相比，CP-Net在各种指标上表现出最佳性能。因此，CP-Net有望帮助解决与3D点云完成相关的各种问题。其源代码可在https://github.com/ark1234/CP-Net上获得。
Point clouds measured by 3D scanning devices often have partially missing data due to the view positioning of the scanner. The missing data can reduce the performance of a point cloud in downstream tasks such as segmentation, location, and pose estimation. Consequently, 3D point cloud completion aims to predict the missing regions of incomplete objects for these fundamental 3D vision tasks. However, predicting the complete object can easily diminish the detail or structure of a measured region, which usually does not require repair. This study proposes a novel neural network architecture, Cosmos Propagation Network (CP-Net), for 3D point cloud completion. CP-Net extracts latent features in different scales from incomplete point clouds used as input. For point cloud generation, we propose a novel point expand method using a Mirror Expand module. Compared with existing methods, our Mirror Expand module introduces less information redundancy, which makes the distribution of points more reliable. CP-Net predicts the details of missing regions and maintains a clear general structure. The performance of CP-Net on several benchmarks was compared to that of current baseline methods. Compared to the existing methods, CP-Net showed the best performance for various metrics. Thus, CP-Net is expected to help address various problems related to 3D point cloud completion. Its source code is available at https://github.com/ark1234/CP-Net.