We consider the task of generating realistic 3D shapes, which is useful for a variety of applications such as automatic scene generation and physical simulation. Compared to other 3D representations like voxels and point clouds, meshes are more desirable in practice, because (1) they enable easy and arbitrary manipulation of shapes for relighting and simulation, and (2) they can fully leverage the power of modern graphics pipelines which are mostly optimized for meshes. Previous scalable methods for generating meshes typically rely on sub-optimal post-processing, and they tend to produce overly-smooth or noisy surfaces without fine-grained geometric details. To overcome these shortcomings, we take advantage of the graph structure of meshes and use a simple yet very effective generative modeling method to generate 3D meshes. Specifically, we represent meshes with deformable tetrahedral grids, and then train a diffusion model on this direct parametrization. We demonstrate the effectiveness of our model on multiple generative tasks.

翻译：我们研究生成逼真3D形状的任务，该任务对于自动场景生成和物理模拟等多种应用具有实用价值。与体素和点云等其他3D表示相比，网格在实际应用中更具优势，因为：（1）它们能够对形状进行简便且任意地操作以用于重新光照和仿真；（2）它们可充分利用现代图形管线的能力——这类管线主要针对网格进行优化。先前可扩展的网格生成方法通常依赖次优的后处理步骤，并且容易产生过度平滑或带有噪声的表面，缺乏精细的几何细节。为解决这些不足，我们利用网格的图结构，采用一种简单但极其有效的生成建模方法来生成3D网格。具体而言，我们使用可变形四面体网格表示对象，并在此直接参数化基础上训练扩散模型。我们在多个生成任务上验证了该模型的有效性。