VoMP: Predicting Volumetric Mechanical Property Fields
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918362711326720 |
|---|---|
| author | Dagli, Rishit Xiang, Donglai Modi, Vismay Loop, Charles Tsang, Clement Fuji Chen, Anka He Hu, Anita State, Gavriel Levin, David I. W. Shugrina, Maria |
| author_facet | Dagli, Rishit Xiang, Donglai Modi, Vismay Loop, Charles Tsang, Clement Fuji Chen, Anka He Hu, Anita State, Gavriel Levin, David I. W. Shugrina, Maria |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VoMP: Predicting Volumetric Mechanical Property Fields Dagli, Rishit Xiang, Donglai Modi, Vismay Loop, Charles Tsang, Clement Fuji Chen, Anka He Hu, Anita State, Gavriel Levin, David I. W. Shugrina, Maria Computer Vision and Pattern Recognition Graphics Machine Learning 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. |
| title | VoMP: Predicting Volumetric Mechanical Property Fields |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning |
| url | https://arxiv.org/abs/2510.22975 |