Mesh generation is of great value in various applications involving computer graphics and virtual content, yet designing generative models for meshes is challenging due to their irregular data structure and inconsistent topology of meshes in the same category. In this work, we design a novel sparse latent point diffusion model for mesh generation. Our key insight is to regard point clouds as an intermediate representation of meshes, and model the distribution of point clouds instead. While meshes can be generated from point clouds via techniques like Shape as Points (SAP), the challenges of directly generating meshes can be effectively avoided. To boost the efficiency and controllability of our mesh generation method, we propose to further encode point clouds to a set of sparse latent points with point-wise semantic meaningful features, where two DDPMs are trained in the space of sparse latent points to respectively model the distribution of the latent point positions and features at these latent points. We find that sampling in this latent space is faster than directly sampling dense point clouds. Moreover, the sparse latent points also enable us to explicitly control both the overall structures and local details of the generated meshes. Extensive experiments are conducted on the ShapeNet dataset, where our proposed sparse latent point diffusion model achieves superior performance in terms of generation quality and controllability when compared to existing methods.

翻译：网格生成在涉及计算机图形学和虚拟内容的各种应用中具有重要价值，但由于网格数据的不规则结构以及同一类别中网格拓扑的不一致性，为网格设计生成模型仍具挑战。本研究提出一种新颖的稀疏潜在点扩散模型用于网格生成。关键思路在于将点云视为网格的中间表示，转而建模点云的分布。通过诸如Shape as Points（SAP）等技术，网格可从点云生成，从而有效规避直接生成网格的难题。为提升网格生成方法的效率与可控性，我们进一步将点云编码为一组具有逐点语义有义特征的稀疏潜在点，并在稀疏潜在点空间中训练两个去噪扩散概率模型（DDPM），分别对潜在点位置及其对应特征的分布进行建模。研究发现，在此潜在空间中采样比直接采样稠密点云更快。此外，稀疏潜在点还能显式控制生成网格的整体结构与局部细节。在ShapeNet数据集上的大量实验表明，与现有方法相比，本文提出的稀疏潜在点扩散模型在生成质量与可控性方面均表现优异。