US 11,854,120 B2
Techniques for reducing distractions in an image
Kfir Aberman, San Mateo, CA (US); Yael Pritch Knaan, Mountain View, CA (US); David Edward Jacobs, Mountain View, CA (US); and Orly Liba, Palo Alto, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Sep. 28, 2021, as Appl. No. 17/487,741.
Prior Publication US 2023/0094723 A1, Mar. 30, 2023
Int. Cl. G06T 11/00 (2006.01); G06N 20/00 (2019.01); G06T 5/00 (2006.01); G06T 11/60 (2006.01)
CPC G06T 11/001 (2013.01) [G06N 20/00 (2019.01); G06T 5/005 (2013.01); G06T 11/60 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for reducing a distractor object in a first image, the method comprising:
accessing, by one or more computing devices, a mask and the first image having the distractor object, wherein the mask indicates a region of interest associated with the first image, and wherein the distractor object is inside the region of interest and has one or more pixels with an original attribute;
processing, using a machine-learned inpainting model, the first image and the mask to generate an inpainted image, wherein the one or more pixels in the inpainted image has an inpainted attribute in one or more chromaticity channels;
determining a palette transform based a comparison of the first image and the inpainted image, wherein the one or more pixels in the palette transform have a transform attribute in the one or more chromaticity channels, the transform attribute being different than the inpainted attribute; and
processing the first image to generate a recolorized image, wherein the one or more pixels of the distractor object in the recolorized image has a recolorized attribute based on the transform attribute of the determined palette transform.