Photorealistic facial texture inference using deep neural networks
US10497172B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 1, 2017 |
| Grant date | Dec 3, 2019 |
| Priority date | — |
| Expiry date | Jun 25, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V40/164
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for generating three-dimensional facial models and photorealistic textures from inferences using deep neural networks relies upon generating a low frequency and a high frequency albedo map of the full and partial face, respectively. Then, the high frequency albedo map may be used for comparison with correlation matrices generated by a neural network trained by a large scale, high-resolution facial dataset with simulated partial visibility. The corresponding correlation matrices of the complete facial textures can then be retrieved. Finally, a full facial texture map may be synthesized, using convex combinations of the correlation matrices. A photorealistic facial texture for the three-dimensional face rendering can be obtained through optimization using the deep neural network and a loss function that incorporates the blended target correlation matrices.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.