Action-conditional implicit dynamics of deformable objects
US12165258B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 10, 2022 |
| Grant date | Dec 10, 2024 |
| Priority date | — |
| Expiry date | Apr 8, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2219/2021
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
One or more machine learning models (MLMs) may learn implicit 3D representations of geometry of an object and of dynamics of the object from performing an action on the object. Implicit neural representations may be used to reconstruct high-fidelity full geometry of the object and predict a flow-based dynamics field from one or more images, which may provide a partial view of the object. Correspondences between locations of an object may be learned based at least on distances between the locations on a surface corresponding to the object, such as geodesic distances. The distances may be incorporated into a contrastive learning loss function to train one or more MLMs to learn correspondences between locations of the object, such as a correspondence embedding field. The correspondences may be used to evaluate state changes when evaluating one or more actions that may be performed on the object.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.