US 12,340,442 B2
Stylizing input images
Jonathon Shlens, San Francisco, CA (US); Vincent Dumoulin, Montreal (CA); and Manjunath Kudlur Venkatakrishna, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Sep. 6, 2023, as Appl. No. 18/242,723.
Application 18/242,723 is a continuation of application No. 16/681,391, filed on Nov. 12, 2019, granted, now 11,776,167.
Application 16/681,391 is a continuation of application No. 16/380,010, filed on Apr. 10, 2019, granted, now 10,535,164, issued on Jan. 14, 2020.
Application 16/380,010 is a continuation of application No. PCT/US2017/057657, filed on Oct. 20, 2017.
Claims priority of provisional application 62/411,414, filed on Oct. 21, 2016.
Prior Publication US 2023/0410389 A1, Dec. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 11/00 (2006.01); G06F 18/214 (2023.01); G06F 18/40 (2023.01); G06N 3/04 (2023.01); G06N 3/0464 (2023.01); G06N 3/08 (2023.01); G06N 3/096 (2023.01)
CPC G06T 11/001 (2013.01) [G06F 18/214 (2023.01); G06F 18/40 (2023.01); G06N 3/04 (2013.01); G06N 3/0464 (2023.01); G06N 3/08 (2013.01); G06N 3/096 (2023.01); G06T 11/00 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for processing an input image to generate a stylized image using a style transfer neural network, the style transfer neural network comprising a particular neural network layer between a first neural network layer and a second neural network layer, the method comprising:
receiving, by a computing system, an input comprising an input image and input style data, the input style data identifying at least one image style to be applied to the input image to generate a stylized image that is in an input style;
obtaining, by the computing system, parameter values for the input style;
setting current values of parameters of the particular neural network layer to be the obtained parameter values for the input style without modifying current values of parameters of the first neural network layer and the second neural network layer; and
processing the input image, using the style transfer neural network having the current values of parameters of the particular neural network layer set to be the obtained parameter values for the input style and the current values of parameters of the first neural network layer and the second neural network layer unchanged, to generate the stylized image,
wherein a particular neural network output of the particular neural network layer is provided as input to the second neural network layer and a second layer output of the second neural network layer is processed to generate the stylized image.