VoMP: Predicting Volumetric Mechanical Property Fields
This addresses the labor-intensive process of hand-crafting mechanical properties for physical simulation, primarily benefiting researchers and practitioners in computer graphics, robotics, and engineering, but it appears incremental as it builds on existing representation and transformer techniques.
The paper tackles the problem of predicting spatially-varying mechanical properties (Young's modulus, Poisson's ratio, density) for 3D objects, which are typically hand-crafted, by introducing VoMP, a feed-forward method that aggregates multi-view features and uses a Geometry Transformer to predict per-voxel material latent codes from a learned physically plausible manifold. Experiments show VoMP far outperforms prior methods in accuracy and speed, though specific numerical gains are not provided.
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.