US 12,277,639 B2
Generating virtual hairstyle using latent space projectors
Aleksandr Belskikh, London (GB); Menglei Chai, Los Angeles, CA (US); Antoine Chassang, London (GB); Anna Kovalenko, London (GB); and Pavel Savchenkov, London (GB)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Dec. 30, 2022, as Appl. No. 18/149,007.
Prior Publication US 2024/0221259 A1, Jul. 4, 2024
Int. Cl. G06T 13/40 (2011.01); G06N 3/094 (2023.01); G06T 19/00 (2011.01)
CPC G06T 13/40 (2013.01) [G06N 3/094 (2023.01); G06T 19/006 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
generating, by one or more hardware processors, a first image of a face using a trained generative adversarial network (GAN) model;
applying, by the one or more hardware processors, three-dimensional (3D) virtual hair on the first image generated by the trained GAN model to generate a second image with 3D virtual hair;
projecting, by the one or more hardware processors, the second image with 3D virtual hair into a GAN latent space to generate a third image with virtual hair;
performing, by the one or more hardware processors, a blend of the virtual hair with the generated first image of the face to generate a new image with new hair that corresponds to the 3D virtual hair;
training, by the one or more hardware processors, a neural network that receives the second image with the 3D virtual hair and provides an output image with virtual hair; and
generating, by the one or more hardware processors, using the trained neural network, a particular output image with hair based on a particular input image with 3D virtual hair.