Patent · US Active

Non-linear latent to latent model for multi-attribute face editing

US11823490B2 · kind B2 · utility

0Cited by
4References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 8, 2021
Grant dateNov 21, 2023
Priority date
Expiry dateJun 16, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/172
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods for image processing are described. One or more embodiments of the present disclosure identify a latent vector representing an image of a face, identify a target attribute vector representing a target attribute for the image, generate a modified latent vector using a mapping network that converts the latent vector and the target attribute vector into a hidden representation having fewer dimensions than the latent vector, wherein the modified latent vector is generated based on the hidden representation, and generate a modified image based on the modified latent vector, wherein the modified image represents the face with the target attribute.

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