US 12,444,020 B2
Flexible image aspect ratio using machine learning
Xiao Feng, Mountain View, CA (US); Yuanzhen Li, Mountain View, CA (US); Yihui Wang, Mountain View, CA (US); Omer Gimenez Llach, Mountain View, CA (US); Han Xu, Mountain View, CA (US); Mengjie Wang, Mountain View, CA (US); Huiwen Chang, Mountain View, CA (US); AJ Maschinot, Mountain View, CA (US); and Dilip Krishnan, Mountain View, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 18/028,063
Filed by GOOGLE LLC, Mountain View, CA (US)
PCT Filed May 20, 2022, PCT No. PCT/CN2022/094121
§ 371(c)(1), (2) Date Mar. 23, 2023,
PCT Pub. No. WO2023/221093, PCT Pub. Date Nov. 23, 2023.
Prior Publication US 2024/0311960 A1, Sep. 19, 2024
Int. Cl. G06T 3/4046 (2024.01)
CPC G06T 3/4046 (2013.01) 20 Claims
OG exemplary drawing
 
1. A method for adjusting an aspect ratio of an image, the method comprising:
receiving, at one or more processors, an image having a first aspect ratio;
obtaining, by the one or more processors, a selection of a second aspect ratio for a display area of a display in which to present the image, wherein the second aspect ratio is different from the first aspect ratio;
extending, by the one or more processors, the image beyond at least one dimension of the display area to include one or more additional features which were not included in the image using a first machine learning model, such that the extended image can be cropped into a plurality of aspect ratios;
automatically selecting, by the one or more processors, a region of interest within the extended image using a second machine learning model;
automatically cropping, by the one or more processors, the extended image around the selected region of interest by selecting a portion of the extended image that has an aspect ratio which matches the second aspect ratio of the display area; and
providing, by the one or more processors, the cropped image for presentation within the display area of the display.