US 11,915,133 B2
Techniques for smooth region merging in image editing
Ratheesh Kalarot, San Jose, CA (US); Kevin Wampler, Seattle, WA (US); Jingwan Lu, Santa Clara, CA (US); Jakub Fiser, Milton Keyne (GB); Elya Shechtman, Seattle, WA (US); Aliakbar Darabi, Seattle, WA (US); and Alexandru Vasile Costin, Monte Sereno, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Sep. 7, 2021, as Appl. No. 17/468,546.
Claims priority of provisional application 63/092,980, filed on Oct. 16, 2020.
Prior Publication US 2022/0122308 A1, Apr. 21, 2022
Int. Cl. G06K 9/00 (2022.01); G06N 3/08 (2023.01); G06F 3/04845 (2022.01); G06F 3/04847 (2022.01); G06T 11/60 (2006.01); G06N 20/20 (2019.01); G06T 5/00 (2006.01); G06T 5/20 (2006.01); G06T 3/00 (2006.01); G06T 3/40 (2006.01); G06T 11/00 (2006.01); G06F 18/40 (2023.01); G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01); G06N 3/045 (2023.01)
CPC G06N 3/08 (2013.01) [G06F 3/04845 (2013.01); G06F 3/04847 (2013.01); G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/2163 (2023.01); G06F 18/40 (2023.01); G06N 3/045 (2023.01); G06N 20/20 (2019.01); G06T 3/0006 (2013.01); G06T 3/0093 (2013.01); G06T 3/40 (2013.01); G06T 3/4038 (2013.01); G06T 3/4046 (2013.01); G06T 5/005 (2013.01); G06T 5/20 (2013.01); G06T 11/001 (2013.01); G06T 11/60 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01); G06T 2210/22 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
cropping, by a computing system, an input image around a region to be edited to produce a cropped input image;
applying, by the computing system, an affine transformation to the cropped input image to produce a rotated cropped input image;
providing, by the computing system, the rotated cropped input image as input to a machine learning model to generate a latent space representation of the rotated cropped input image;
editing, by the computing system, the latent space representation to generate an edited latent space representation;
providing, by the computing system, the edited latent space representation as input to a trained generator neural network implemented by the computing system;
generating, by the generator neural network, a generated edited image;
applying, by the computing system, an inverse affine transformation to the generated edited image to generate a rotated generated edited image;
aligning, by the computing system, an identified segment of the rotated generated edited image with an identified corresponding segment of the input image to produce an aligned rotated generated edited image; and
blending, by the computing system, the aligned rotated generated edited image with the input image to generate an edited output image.