论文标题
连续调理的点云产生
Point Cloud Generation with Continuous Conditioning
论文作者
论文摘要
生成模型可用于合成高质量和多样性的3D对象。但是，通常无法控制生成对象的属性。本文提出了一种新颖的生成对抗网络（GAN）设置，该设置生成以连续参数为条件的3D点云形状。在模范应用程序中，我们使用它来指导生成过程，以创建具有自定义形状的3D对象。我们使用辅助分类器gans的概念在多任务设置中制定了这一生成过程。此外，我们建议对生成器标签输入进行采样，以从数据集的内核密度估计（KDE）进行训练。我们的消融表明，这会导致几乎没有样本的地区的大幅度提高。广泛的定量和定性实验表明，我们可以明确控制对象维度，同时保持良好的发电质量和多样性。
Generative models can be used to synthesize 3D objects of high quality and diversity. However, there is typically no control over the properties of the generated object.This paper proposes a novel generative adversarial network (GAN) setup that generates 3D point cloud shapes conditioned on a continuous parameter. In an exemplary application, we use this to guide the generative process to create a 3D object with a custom-fit shape. We formulate this generation process in a multi-task setting by using the concept of auxiliary classifier GANs. Further, we propose to sample the generator label input for training from a kernel density estimation (KDE) of the dataset. Our ablations show that this leads to significant performance increase in regions with few samples. Extensive quantitative and qualitative experiments show that we gain explicit control over the object dimensions while maintaining good generation quality and diversity.
