US 12,002,136 B2
Style try-on with reverse GANs
Rohit Saha, Toronto (CA); and Brendan Duke, Toronto (CA)
Assigned to L'OREAL, Paris (FR)
Filed by L'OREAL, Paris (FR)
Filed on Mar. 3, 2022, as Appl. No. 17/685,675.
Claims priority of provisional application 63/155,842, filed on Mar. 3, 2021.
Claims priority of application No. 2201829 (FR), filed on Mar. 2, 2022.
Prior Publication US 2022/0284646 A1, Sep. 8, 2022
Int. Cl. G06T 11/60 (2006.01); G06N 3/08 (2023.01); G06Q 30/0601 (2023.01); G06T 5/50 (2006.01); G06T 7/11 (2017.01); G06F 3/0482 (2013.01)
CPC G06T 11/60 (2013.01) [G06N 3/08 (2013.01); G06Q 30/0631 (2013.01); G06T 5/50 (2013.01); G06T 7/11 (2017.01); G06F 3/0482 (2013.01); G06T 2200/24 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20212 (2013.01); G06T 2207/30201 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method to perform a style transfer of a style using artificial intelligence (AI), the style comprising a plurality of style attributes, the method comprising:
processing a plurality of images comprising a first image (I1), a second image (I2) and a third image (I3) using an AI network framework comprising a generative adversarial network (GAN) generator and a two stage optimization to generate a synthesized image (IG) comprising an identity represented by the first image (I1) and a style determined from at least one style attribute represented by the second image (I2) and at least one style attribute represented by the third image (I3);
wherein the AI network framework is configured to optimize a latent space of a GAN model to perform the style transfer while disentangling the at least one style attribute represented by the second image (I2) and the at least one style attribute represented by the third image (I3); and
wherein the network framework performs gradient orthogonalization in the two stage optimization to disentangle the at least one style attribute represented by second image (I2) and the at least one style attribute represented by the third image (I3).