首页 | 本学科首页   官方微博 | 高级检索  
     

面向点云三维重建的空间感知对抗神经网络
引用本文:卢林鹏,关柏良,林淑金. 面向点云三维重建的空间感知对抗神经网络[J]. 计算机工程与科学, 2022, 44(7): 1247-1255
作者姓名:卢林鹏  关柏良  林淑金
作者单位:(1.中山大学计算机学院,广东 广州 510006;2.中山大学传播与设计学院,广东 广州 510006)
基金项目:广东省基础与应用基础研究基金(2019A1515011953)
摘    要:为了解决由原始点云数据局部密度稀疏、不均匀或者法向量错误等制约因素引起的重建网格质量问题,利用对抗神经网络中权重共享的特性和对抗的训练过程,提出一种基于对抗网络的点云三维重建方法。首先,利用预测器对网格模型边的偏移量进行预测,从而得到每一个顶点的位移,并进行拓扑保持的顶点重定向,得到新的网格模型。然后,利用判别器中的点云分类器,提取原始点云数据和网格模型表面采样点集的高维特征,并基于高维特征进行空间感知的判别,用于区分原始点云与采样点集数据。最后,使用对抗的训练方式将预测器与判别器的输出数据关联起来,通过多次迭代优化网络模型,从而得到满足点云空间特征的三维网格模型。在不同的点云数据集上进行实验,并使用MeshLab软件进行效果展示,结果表明,该方法能够重建出满足点云空间信息的三维网格模型,同时能够解决粗劣的点云数据引起的网格质量问题。

关 键 词:三维重建  深度学习  网格变形  对抗网络
收稿时间:2021-11-24
修稿时间:2022-01-14

A space-aware adversarial neural networkfor 3D reconstruction of point cloud
LU Lin-peng,GUAN Bo-liang,LIN Shu-jin. A space-aware adversarial neural networkfor 3D reconstruction of point cloud[J]. Computer Engineering & Science, 2022, 44(7): 1247-1255
Authors:LU Lin-peng  GUAN Bo-liang  LIN Shu-jin
Affiliation:(1.School of Computer Science,Sun Yat-sen University,Guangzhou 510006;2.School of Communication and Design,Sun Yat-sen University,Guangzhou 510006,China)
Abstract:In order to overcome the quality problem of reconstructed meshes caused by the restrictive factors such as sparse and uneven density or wrong normal vector of original point cloud data, a three-dimensional reconstruction method of point cloud based on Countermeasure network is proposed by using the characteristics of weight sharing in adversarial neural network and adversarial training process.Firstly, the predictor is used to predict the offset of the edge of the mesh model, so as to obtain the displacement of each vertex, and perform the vertex redirection of the topology preservation to obtain a new mesh. Secondly, the point cloud classifier in the discriminator is used to extract the high-dimensional features of the original point cloud data and the sampled point set of the mesh surface, and the spatial perception discrimination based on the high-dimensional features is performed to distinguish the original point cloud from the samples point set data. Finally, the output data of the predictor and the discriminator are correlated by the adversarial training method, and the network model is optimized through multiple iterations to obtain a three-dimensional mesh model that meets the spatial characteristics of the point cloud. Experiments are carried out on different point cloud datasets, and the results are displayed by using MeshLab software. The results show that the method can reconstruct the 3D mesh model that meets the spatial information of point cloud, and overcome the mesh quality problems caused by poor point cloud data.
Keywords:3D reconstruction  deep learning  mesh deformation  adversarial network  
点击此处可从《计算机工程与科学》浏览原始摘要信息
点击此处可从《计算机工程与科学》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号