arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.22975cs.CVcs.GRcs.LG
收藏

VoMP:预测体积机械属性场

VoMP: Predicting Volumetric Mechanical Property Fields

NVIDIA;University of Toronto(多伦多大学)

Rishit Dagli, Donglai Xiang, Vismay Modi, Charles Loop, Clement Fuji Tsang, Anka He Chen, Anita Hu, Gavriel State, David I. W. Levin, Maria Shugrina

AI总结:

VoMP通过训练几何变换器预测3D物体的体积机械属性场,结合多视角特征和现实世界数据集,实现高精度和高速度的属性估计。

摘要:

物理模拟依赖于空间变化的机械属性,通常需要繁琐的手工构建。VoMP是一种前馈方法,训练以预测Young模量(E)、泊松比(ν)和密度(ρ)在整个3D物体体积内的属性,无论以何种可以渲染和体素化的表示形式。VoMP聚合每个体素多视角特征,并将其传递给训练好的几何变换器,以预测每个体素的材料潜在代码。这些潜在代码位于物理合理材料的流形上,我们从现实世界数据集中学习,确保解码后的每个体素材料的有效性。为了获得物体级别的训练数据,我们提出了一种结合来自分割3D数据集、材料数据库和视觉-语言模型知识的注释流程,以及一个新的基准。实验表明,VoMP能够准确估计体积属性,其准确性和速度均远超先前方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑