基于动态图卷积的点云补全网络  

Point cloud completion network based on dynamic graph convolution

作　　者：季建杰 刘杰 邵剑飞[1] 张建华 Ji Jianjie;Liu Jie;Shao Jianfei;Zhang Jianhua(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650504,China;Yunnan Police College,Kunming 650223,China;Yunnan Zhongkan Surveying and Mapping Engineering Company,Kunming 650034,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650504 [2]云南警官学院,云南昆明650223 [3]云南中勘测绘工程有限公司,云南昆明650034

出　　处：《电子技术应用》2023年第6期18-23,共6页Application of Electronic Technique

基　　金：国家自然科学基金(61732005)。

摘　　要：大多数传统的深度学习点云补全学习方法仅仅使用了全局特征而忽略了局部特征,为了更好地提取和使用点云的局部特征,提出了一个基于深度学习的端到端点云补全网络。在点云补全网络(PCN)的基础上,编码部分引入针对局部特征改进的动态图卷积(DGCNN),使用多个不同维度的边卷积提取较为丰富的局部特征,并按照距离弱化远点的特征;然后用深度残差网络连接的思想优化网络结构以实现多尺度特征的融合,并加入平均池化弥补全局池化造成的信息损失;在解码部分引入折叠网络(FoldingNet),使输出的点云更加完整。实验结果表明,该点云补全网络相对PCN等点云补全网络有部分提升,验证了新方法的有效性。Most traditional deep learning point cloud complement learning methods only use the global features and ignore the lo‐cal features.In order to better extract and use the local features of point cloud,an end-to-end cloud completion network based on deep learning is proposed in this paper.On the basis of point cloud completion network(PCN),the coding part introduces dy‐namic graph convolution(DGCNN)improved for local features.The edge convolution of multiple different dimensions is used to extract more abundant local features,and weaken the characteristics of the far point according to the distance.Then the network structure is optimized with the idea of deep residual network connection to achieve the fusion of multi-scale features,and the mean pooling method is added to compensate for the information loss caused by global pooling.In the decoder part,FoldingNet was used to make the output point cloud complete.The experimental results show that the point cloud completion network is par‐tially improved compared with PCN and other point cloud completion networks,which verifies the effectiveness of the new method.

关 键 词：图像处理 三维点云 卷积神经网络 形状补全 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]