Physical simulation relies on spatially-varying mechanical properties, often laboriously hand-crafted. VoMP is a feed-forward method trained to predict Young's modulus ($E$), Poisson's ratio ($ν$), and density ($ρ$) throughout the volume of 3D objects, in any representation that can be rendered and voxelized. VoMP aggregates per-voxel multi-view features and passes them to our trained Geometry Transformer to predict per-voxel material latent codes. These latents reside on a manifold of physically plausible materials, which we learn from a real-world dataset, guaranteeing the validity of decoded per-voxel materials. To obtain object-level training data, we propose an annotation pipeline combining knowledge from segmented 3D datasets, material databases, and a vision-language model, along with a new benchmark. Experiments show that VoMP estimates accurate volumetric properties, far outperforming prior art in accuracy and speed.

翻译：物理仿真依赖于空间变化的力学特性，这些特性通常需要耗费大量精力手工制作。VoMP是一种前馈式训练方法，旨在预测三维物体整个体积内的杨氏模量（$E$）、泊松比（$ν$）和密度（$ρ$），适用于任何可渲染并体素化的表示形式。VoMP通过聚合每个体素的多视角特征，并将其输入我们训练的Geometry Transformer，以预测每个体素的材料潜在编码。这些潜在编码位于物理合理材料构成的流形上，该流形通过真实世界数据集学习获得，从而确保解码出的每个体素材料的有效性。为获取物体级训练数据，我们提出了一种标注流程，该流程结合了分割三维数据集、材料数据库和视觉语言模型的知识，并引入了一个新的基准测试。实验表明，VoMP能够准确估计体积特性，在精度和速度上远超现有技术。