DeepCAD: A Deep Generative Network for Computer-Aided Design Models
DeepCAD: A Deep Generative Network for Computer-Aided Design Models
复制标题
DOI：
10.1109/iccv48922.2021.00670
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Rundi Wu;Chang Xiao;Changxi Zheng
中科院分区：
文献类型：
--
作者：
Rundi Wu;Chang Xiao;Changxi Zheng
3D形状的深度生成模型已经引起了大量的研究兴趣。然而，几乎所有的方法都生成离散的形状表示，如体素、点云和多边形网格。我们提出了第一个3D生成模型的一个完全不同的形状表示-描述一个形状作为一个序列的计算机辅助设计（CAD）操作。与网格和点云不同，CAD模型对3D形状的用户创建过程进行编码，广泛用于许多工业和工程设计任务。然而，CAD操作的顺序和不规则结构对现有的3D生成模型提出了重大挑战。通过类比CAD操作和自然语言，我们提出了一个基于Transformer的CAD生成网络。我们证明了我们的模型的形状自动编码和随机形状生成的性能。为了训练我们的网络，我们创建了一个由178，238个模型及其CAD构造序列组成的新CAD数据集。我们已经公开了这个数据集，以促进未来对这个主题的研究。
Deep generative models of 3D shapes have received a great deal of research interest. Yet, almost all of them generate discrete shape representations, such as voxels, point clouds, and polygon meshes. We present the first 3D generative model for a drastically different shape representation— describing a shape as a sequence of computer-aided design (CAD) operations. Unlike meshes and point clouds, CAD models encode the user creation process of 3D shapes, widely used in numerous industrial and engineering design tasks. However, the sequential and irregular structure of CAD operations poses significant challenges for existing 3D generative models. Drawing an analogy between CAD operations and natural language, we propose a CAD generative network based on the Transformer. We demonstrate the performance of our model for both shape autoencoding and random shape generation. To train our network, we create a new CAD dataset consisting of 178,238 models and their CAD construction sequences. We have made this dataset publicly available to promote future research on this topic.