While the community of 3D point cloud generation has witnessed a big growth in recent years, there still lacks an effective way to enable intuitive user control in the generation process, hence limiting the general utility of such methods. Since an intuitive way of decomposing a shape is through its parts, we propose to tackle the task of controllable part-based point cloud generation. We introduce DiffFacto, a novel probabilistic generative model that learns the distribution of shapes with part-level control. We propose a factorization that models independent part style and part configuration distributions and presents a novel cross-diffusion network that enables us to generate coherent and plausible shapes under our proposed factorization. Experiments show that our method is able to generate novel shapes with multiple axes of control. It achieves state-of-the-art part-level generation quality and generates plausible and coherent shapes while enabling various downstream editing applications such as shape interpolation, mixing, and transformation editing. Project website: https://difffacto.github.io/

翻译：尽管近年来三维点云生成领域取得了显著发展，但在生成过程中实现直观的用户控制仍缺乏有效方法，从而限制了此类方法的通用性。由于通过部件分解形状是一种直观的方式，我们提出解决基于部件可控的点云生成任务。本文提出DiffFacto——一种新型概率生成模型，能够学习具有部件级别控制的形状分布。我们提出一种分解方法，分别对独立部件风格和部件配置分布进行建模，并引入新型交叉扩散网络，使得在本文分解框架下能够生成连贯且合理的形状。实验表明，我们的方法能够生成具有多轴控制能力的新颖形状，在部件级生成质量上达到最优水平，同时生成合理且连贯的形状，并支持形状插值、混合与变换编辑等下游编辑应用。项目网站：https://difffacto.github.io/