论文标题
LPMNET：3D点云的潜在零件修改和生成
LPMNet: Latent Part Modification and Generation for 3D Point Clouds
论文作者
论文摘要
在本文中，我们将重点放在潜在的修改和生成3D点云对象模型相对于其语义部分。与现有的方法不同，将单独的网络用于部分生成和组装，我们提出了一个端到端自动编码器模型，该模型可以处理两个语义零件和全局形状的生成和修改。所提出的方法支持3D点云模型与不同部分组成之间的零件交换，以直接编辑潜在表示形式来形成新模型。这种整体方法不需要基于部分的培训来学习零件表示，并且除了标准重建损失外没有引入任何额外的损失。该实验证明了所提出的方法具有不同对象类别和不同点的鲁棒性。该方法可以通过集成诸如gan和vaes之类的生成模型来生成新的模型，并可以通过集成分割模块来与未注释的点云一起工作。
In this paper, we focus on latent modification and generation of 3D point cloud object models with respect to their semantic parts. Different to the existing methods which use separate networks for part generation and assembly, we propose a single end-to-end Autoencoder model that can handle generation and modification of both semantic parts, and global shapes. The proposed method supports part exchange between 3D point cloud models and composition by different parts to form new models by directly editing latent representations. This holistic approach does not need part-based training to learn part representations and does not introduce any extra loss besides the standard reconstruction loss. The experiments demonstrate the robustness of the proposed method with different object categories and varying number of points. The method can generate new models by integration of generative models such as GANs and VAEs and can work with unannotated point clouds by integration of a segmentation module.
