论文标题
渐进的条件生成对抗网络，用于生成密集和彩色的3D点云
A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds
论文作者
论文摘要
在本文中，我们引入了一个新颖的条件生成对抗网络，该网络以无监督的方式为各种对象类别创建密集的3D点云，并为各种颜色提供颜色。为了克服在高分辨率下捕获复杂细节的困难，我们提出了一个点变压器，该变压器通过使用图卷积逐渐发展网络。该网络由叶子输出层和一组初始分支组成。每个训练迭代都会将点向量演变为分辨率增加的点云。固定数量的迭代次数后，通过复制最后一个分支来增加分支的数量。实验结果表明，我们的网络能够学习和模仿3D数据分布，并在多个分辨率下产生彩色点云，并具有细节。
In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner. To overcome the difficulty of capturing intricate details at high resolutions, we propose a point transformer that progressively grows the network through the use of graph convolutions. The network is composed of a leaf output layer and an initial set of branches. Every training iteration evolves a point vector into a point cloud of increasing resolution. After a fixed number of iterations, the number of branches is increased by replicating the last branch. Experimental results show that our network is capable of learning and mimicking a 3D data distribution, and produces colored point clouds with fine details at multiple resolutions.
