Patent · US Active

Semantic deep face models

US11276231B2 · kind B2 · utility

2Cited by
0References
21Claims
0Family size

Assignees

Inventors

Key dates

Filing dateMar 4, 2020
Grant dateMar 15, 2022
Priority date
Expiry dateMar 4, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2219/2021
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Techniques are disclosed for training and applying nonlinear face models. In embodiments, a nonlinear face model includes an identity encoder, an expression encoder, and a decoder. The identity encoder takes as input a representation of a facial identity, such as a neutral face mesh minus a reference mesh, and outputs a code associated with the facial identity. The expression encoder takes as input a representation of a target expression, such as a set of blendweight values, and outputs a code associated with the target expression. The codes associated with the facial identity and the facial expression can be concatenated and input into the decoder, which outputs a representation of a face having the facial identity and expression. The representation of the face can include vertex displacements for deforming the reference mesh.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.