US 12,260,485 B2
Cascaded domain bridging for image generation
Guoxian Song, Los Angeles, CA (US); Shen Sang, Los Angeles, CA (US); Tiancheng Zhi, Los Angeles, CA (US); Jing Liu, Los Angeles, CA (US); and Linjie Luo, Los Angeles, CA (US)
Assigned to Lemon Inc., Grand Cayman (KY)
Filed by Lemon Inc., Grand Cayman (KY)
Filed on Oct. 12, 2022, as Appl. No. 18/046,077.
Prior Publication US 2024/0135627 A1, Apr. 25, 2024
Int. Cl. G06T 15/00 (2011.01); G06T 7/11 (2017.01); G06T 15/02 (2011.01)
CPC G06T 15/02 (2013.01) [G06T 7/11 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30201 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of generating a style image, the method comprising:
receiving an input image of a subject;
encoding the input image using a first encoder of a generative adversarial network (GAN) to obtain a first latent code;
decoding the first latent code using a first decoder of the GAN to obtain a normalized style image of the subject, wherein:
the GAN is trained using a loss function according to semantic regions of the input image and the normalized style image, and
a distribution prior of a W+ space is modeled for training the GAN by inverting a dataset of real face images using a second encoder that is pre-trained.