US 12,327,328 B2
Aesthetics-guided image enhancement
Xiaohui Shen, San Jose, CA (US); Zhe Lin, Fremont, CA (US); Xin Lu, Mountain View, CA (US); Sarah Aye Kong, Cupertino, CA (US); I-Ming Pao, Palo Alto, CA (US); and Yingcong Chen, Hong Kong (TW)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Jul. 19, 2021, as Appl. No. 17/379,622.
Application 17/379,622 is a division of application No. 15/928,706, filed on Mar. 22, 2018, granted, now 11,069,030.
Prior Publication US 2021/0350504 A1, Nov. 11, 2021
Int. Cl. G06T 5/00 (2024.01); G06V 10/44 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01); G06V 30/19 (2022.01)
CPC G06T 5/00 (2013.01) [G06V 10/454 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01); G06V 30/19173 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 15 Claims
OG exemplary drawing
 
1. One or more non-transitory computer-readable media having a plurality of executable instructions embodied thereon, which, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:
obtaining scored images, wherein a plurality of images are scored based on aesthetic attributes;
designating the scored images that have aesthetic scores within a predefined range as input images;
designating the scored images that have aesthetic scores above a predefined threshold as reference images;
training an aesthetic image enhancing neural network system using the input images with a first neural network and reference images with a second neural network, wherein the trained aesthetic image enhancing neural network system is used to generate an enhanced image from an image input;
analyzing portions of the scored images using a segmentation network, wherein analyzing portions of the scored images using the segmentation network causes adaptive adjustments by the first neural network; and
outputting the enhanced image, wherein the enhanced image has increased aesthetics when compared with the image input into the trained aesthetic image enhancing neural network system.