Creation of photorealistic 3D avatars using deep neural networks
US11138781B1 · kind B1 · utility
1Cited by
5References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 1, 2020 |
| Grant date | Oct 5, 2021 |
| Priority date | — |
| Expiry date | Apr 1, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L13/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-implemented method for the automatic generation of photorealistic 3D avatars. The method includes generating, using machine learning network, a plurality of 2D photorealistic facial images; generating, using a model agnostic meta-learner, a plurality of 2D photorealistic facial expression images based on the plurality of 2D photorealistic facial images; and generating a plurality of 3D photorealistic avatars based on the plurality of 2D photorealistic facial expression images.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.