US 12,406,377 B2
Techniques for reducing a distraction in an image
Kfir Aberman, San Mateo, CA (US); David Edward Jacobs, Mountain View, CA (US); Kai Jochen Kohlhoff, Mountain View, CA (US); Michael Rubinstein, Natick, MA (US); Yossi Gandelsman, Berkeley, CA (US); Junfeng He, Fremont, CA (US); Inbar Mosseri, Raanana (IL); and Yael Pritch Knaan, Tel Aviv (IL)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jul. 1, 2022, as Appl. No. 17/856,370.
Claims priority of provisional application 63/218,096, filed on Jul. 2, 2021.
Prior Publication US 2023/0015117 A1, Jan. 19, 2023
Int. Cl. G06T 11/00 (2006.01); G06T 3/18 (2024.01); G06T 7/11 (2017.01); G06T 7/194 (2017.01); G06V 40/20 (2022.01)
CPC G06T 7/194 (2017.01) [G06T 3/18 (2024.01); G06T 7/11 (2017.01); G06T 11/001 (2013.01); G06V 40/20 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for configuring an image editing operator for reducing a distractor in raw image data, the method comprising:
accessing, by one or more computing devices, the raw image data and a mask, wherein the mask indicates a region of interest associated with the raw image data;
processing, by the one or more computing devices, the raw image data and the mask with the image editing operator to generate processed image data;
processing, by the one or more computing devices, at least the processed image data within the region of interest with a trained saliency model to generate a saliency map that provides saliency values for at least the processed image data within the region of interest;
evaluating, by the one or more computing devices, a saliency loss function that compares the saliency values provided by the saliency map for the processed image data within the region of interest to one or more target saliency values; and
modifying, by the one or more computing devices, one or more parameter values of the image editing operator for processing the raw image data into the processed image data based at least in part on the saliency loss function to reduce the distractor in the raw image.