Transferable foundation models for geometric tasks on point cloud representations: geometric neural operators
Guardado en:
| Publicado en: | Machine Learning : Science and Technology vol. 6, no. 4 (Dec 2025), p. 045045 |
|---|---|
| Autor principal: | |
| Otros Autores: | |
| Publicado: |
IOP Publishing
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3272720416 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2632-2153 | ||
| 024 | 7 | |a 10.1088/2632-2153/ae1bf8 |2 doi | |
| 035 | |a 3272720416 | ||
| 045 | 2 | |b d20251201 |b d20251231 | |
| 100 | 1 | |a Quackenbush, B | |
| 245 | 1 | |a Transferable foundation models for geometric tasks on point cloud representations: geometric neural operators | |
| 260 | |b IOP Publishing |c Dec 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a We introduce methods for obtaining pretrained geometric neural operators (GNPs) that can serve as basal foundation models for use in obtaining geometric features. These can be used within data processing pipelines for machine learning tasks and numerical methods. We show how our GNPs can be trained to learn robust latent representations for the differential geometry of point-clouds to provide estimates of metric, curvature, and other shape-related features. We demonstrate how our pre-trained GNPs can be used (i) to estimate the geometric properties of surfaces of arbitrary shape and topologies with robustness in the presence of noise, (ii) to approximate solutions of geometric partial differential equations on manifolds, and (iii) to solve equations for shape deformations such as curvature driven flows. We release codes and weights for using GNPs in the package <ext-link ext-link-type="uri" xlink3ahref="https://github.com/atzberg/geo_neural_op">geo_neural_op</ext-link>. This allows for incorporating our pre-trained GNPs as components for reuse within existing and new data processing pipelines. The GNPs also can be used as part of numerical solvers involving geometry or as part of methods for performing inference and other geometric tasks. | |
| 653 | |a Data processing | ||
| 653 | |a Partial differential equations | ||
| 653 | |a Curvature | ||
| 653 | |a Machine learning | ||
| 653 | |a Differential geometry | ||
| 653 | |a Operators (mathematics) | ||
| 653 | |a Numerical methods | ||
| 653 | |a Cognitive tasks | ||
| 653 | |a Representations | ||
| 653 | |a Topology | ||
| 700 | 1 | |a Atzberger, P J | |
| 773 | 0 | |t Machine Learning : Science and Technology |g vol. 6, no. 4 (Dec 2025), p. 045045 | |
| 786 | 0 | |d ProQuest |t Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3272720416/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3272720416/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |