用3D物体图像预测内部力学属性，自动生成真实可行的材料分布。
VoMP: Predicting Volumetric Mechanical Property Fields
- 通过多视角特征聚合与几何转换器，预测体素级材料潜码
- 在真实数据集上训练，生成的杨氏模量、泊松比和密度均符合物理规律
- 适合需要快速高精度材料建模的仿真与设计场景
物理仿真依赖空间变化的力学属性，通常需人工精心设计。VoMP是一种前馈方法，可预测3D物体体积内任意表示形式的杨氏模量（E）、泊松比（ν）和密度（ρ），前提是该表示可渲染并体素化。VoMP聚合体素级多视角特征，并通过训练好的几何变换器预测体素级材料潜码。这些潜码位于由真实世界数据学习得到的物理合理材料流形上，确保解码后的体素材料具有物理有效性。为获取对象级训练数据，我们提出一个结合分割3D数据集、材料数据库和视觉-语言模型的标注流程，并构建了一个新基准。实验表明，VoMP在准确性和速度上均显著优于现有方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。