US 12,299,799 B2
Cascaded domain bridging for image generation
Shen Sang, Los Angeles, CA (US); Tiancheng Zhi, Los Angeles, CA (US); Guoxian Song, Los Angeles, CA (US); Jing Liu, Los Angeles, CA (US); Linjie Luo, Los Angeles, CA (US); Chunpong Lai, Los Angeles, CA (US); Weihong Zeng, Beijing (CN); Jingna Sun, Beijing (CN); and Xu Wang, Beijing (CN)
Assigned to Lemon Inc., Grand Cayman (KY); and Beijing Zitiao Network Technology Co., Ltd., Beijing (CN)
Filed by Lemon Inc., Grand Cayman (KY); and Beijing Zitiao Network Technology Co., Ltd., Beijing (CN)
Filed on Oct. 12, 2022, as Appl. No. 18/046,073.
Prior Publication US 2024/0135621 A1, Apr. 25, 2024
Int. Cl. G06T 15/00 (2011.01); G06T 7/62 (2017.01); G06V 10/56 (2022.01); G06V 10/74 (2022.01); G06V 10/75 (2022.01)
CPC G06T 15/00 (2013.01) [G06T 7/62 (2017.01); G06V 10/56 (2022.01); G06V 10/751 (2022.01); G06V 10/761 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/30201 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method of generating a stylized 3D avatar, the method comprising:
receiving an input image of a user;
generating, using a generative adversarial network (GAN) generator, a stylized image, based on the input image;
providing the stylized image to a first model to generate a first plurality of parameters, the first plurality of parameters comprising one or more discrete parameters and one or more continuous parameters, the one or more continuous parameters comprise head characteristics, mouth characteristics, nose characteristics, ear characteristics, and eye characteristics, each corresponding to the user, wherein:
the head characteristics comprise a head width, a head length, and a blend shape coefficient for a head shape,
the mouth characteristics comprise a mouth width, a mouth volume, and a mouth position,
the nose characteristics comprise a nose width, a nose height, and a nose position,
the eye characteristics comprise an eye size, an eye spacing, and an eye rotation, and
the ear characteristics comprise an ear size,
providing the stylized image and the first plurality of parameters to a second model, the second model being trained to generate an avatar image;
receiving, from the second model, the avatar image;
comparing the stylized image to the avatar image, based on a loss function, to determine an error;
updating the first model to generate a second plurality of parameters, based on the error, the second plurality of parameters corresponding to the first plurality of parameters; and
providing the second plurality of parameters as an output.