In this work, we propose a novel method for generating 3D point clouds that leverages the properties of hypernetworks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a representation of the object and its 3D surface. The main idea of our HyperCloud method is to build a hypernetwork that returns weights of a particular neural network (target network) trained to map points from prior distribution into a 3D shape. As a consequence, a particular 3D shape can be generated using point-by-point sampling from the prior distribution and transforming the sampled points with the target network. Since the hypernetwork is based on an auto-encoder architecture trained to reconstruct realistic 3D shapes, the target network weights can be considered to be a parametrization of the surface of a 3D shape, and not a standard representation of point cloud usually returned by competitive approaches. We also show that relying on hypernetworks to build 3D point cloud representations offers an elegant and flexible framework. To that point, we further extend our method by incorporating flow-based models, which results in a novel HyperFlow approach.

中文翻译：

---

用于创建 3D 点云的通用超网络框架


在这项工作中，我们提出了一种利用超网络特性生成 3D 点云的新方法。与仅学习 3D 对象表示的现有方法相反，我们的方法同时找到对象及其 3D 表面的表示。我们的 HyperCloud 方法的主要思想是构建一个超网络，该网络返回特定神经网络（目标网络）的权重，该神经网络经过训练，可以将先验分布中的点映射到 3D 形状。因此，可以使用先验分布的逐点采样并使用目标网络变换采样点来生成特定的 3D 形状。由于超网络基于经过训练以重建真实 3D 形状的自动编码器架构，因此目标网络权重可以被视为 3D 形状表面的参数化，而不是通常由竞争方法返回的点云的标准表示。我们还表明，依靠超网络构建 3D 点云表示提供了一个优雅且灵活的框架。为此，我们通过结合基于流的模型进一步扩展了我们的方法，从而产生了一种新颖的 HyperFlow 方法。