Portrait stylization framework to control the similarity between stylized portraits and original photo
AssigneeLemon Inc.
InventorsJing Liu, Chunpong Lai, Guoxian Song, Linjie Luo
Life of this patent
Estimating the term…
Loading patent…
AssigneeLemon Inc.
InventorsJing Liu, Chunpong Lai, Guoxian Song, Linjie Luo
Estimating the term…
Systems and methods directed to controlling the similarity between stylized portraits and an original photo are described. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be blended with latent vectors that best represent a face in the original user portrait image. The resulting blended latent vector may be provided to a generative adversarial network (GAN) generator to generate a controlled stylized image. In examples, one or more layers of the stylized GAN generator may be swapped with one or more layers of the original GAN generator. Accordingly, a user can interactively determine how much stylization vs. personalization should be included in a resulting stylized portrait.
A method for generating a stylized image, the method comprising:
A system, comprising:
A computer-readable storage medium comprising instructions, which when executed by one or more processors, cause the one or more processors to:
Dependencies are inferred from the claim text.