当前位置: X-MOL 学术arXiv.cs.CG › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
arXiv - CS - Computational Geometry Pub Date : 2020-03-19 , DOI: arxiv-2003.08624
Kaichun Mo, He Wang, Xinchen Yan, Leonidas J. Guibas

3D generative shape modeling is a fundamental research area in computer vision and interactive computer graphics, with many real-world applications. This paper investigates the novel problem of generating 3D shape point cloud geometry from a symbolic part tree representation. In order to learn such a conditional shape generation procedure in an end-to-end fashion, we propose a conditional GAN "part tree"-to-"point cloud" model (PT2PC) that disentangles the structural and geometric factors. The proposed model incorporates the part tree condition into the architecture design by passing messages top-down and bottom-up along the part tree hierarchy. Experimental results and user study demonstrate the strengths of our method in generating perceptually plausible and diverse 3D point clouds, given the part tree condition. We also propose a novel structural measure for evaluating if the generated shape point clouds satisfy the part tree conditions.

中文翻译:

PT2PC:学习从零件树条件生成 3D 点云形状

3D 生成形状建模是计算机视觉和交互式计算机图形的基础研究领域,具有许多实际应用。本文研究了从符号部分树表示生成 3D 形状点云几何的新问题。为了以端到端的方式学习这种有条件的形状生成过程,我们提出了一个有条件的 GAN“部分树”到“点云”模型(PT2PC),它可以解开结构和几何因素。所提出的模型通过沿着部件树层次结构自上而下和自下而上地传递消息,将部件树条件合并到架构设计中。给定零件树条件,实验结果和用户研究证明了我们的方法在生成感知上合理且多样化的 3D 点云方面的优势。
更新日期:2020-07-17
down
wechat
bug