US 12,107,914 B2
Realistic neural network based image style transfer
Jaewook Chung, Mountain View, CA (US); Christopher Yale Crutchfield, San Diego, CA (US); and Emre Yamangil, San Francisco, CA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on May 10, 2023, as Appl. No. 18/195,813.
Application 18/195,813 is a continuation of application No. 17/123,493, filed on Dec. 16, 2020, granted, now 11,683,362.
Application 17/123,493 is a continuation of application No. 16/147,705, filed on Sep. 29, 2018, granted, now 10,891,723.
Claims priority of provisional application 62/566,072, filed on Sep. 29, 2017.
Prior Publication US 2023/0283654 A1, Sep. 7, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 67/04 (2022.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06T 5/00 (2006.01); G06T 5/40 (2006.01); G06T 5/92 (2024.01); G06T 7/90 (2017.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 40/16 (2022.01); G06Q 50/00 (2012.01)
CPC H04L 67/04 (2013.01) [G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06T 5/00 (2013.01); G06T 5/40 (2013.01); G06T 5/92 (2024.01); G06T 7/90 (2017.01); G06V 10/7753 (2022.01); G06V 10/82 (2022.01); G06V 40/161 (2022.01); G06V 40/175 (2022.01); G06Q 50/01 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20132 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving an indication of an instruction to modify an initial image comprising a user face, the instruction indicating to change the user face from having a first appearance to having a second appearance;
modifying a user face portion of the initial image using a convolutional neural network, the modified user face portion having the second appearance; and
modifying a non user face portion of the initial image by applying adjustments to the non user face portion, wherein the adjustments are effects selected based on the convolutional neural network used to modified the user face portion.