US 12,249,002 B2
Watermark-based image reconstruction
Innfarn Yoo, Fremont, CA (US); Feng Yang, Sunnyvale, CA (US); and Xiyang Luo, Pasadena, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 17/764,445
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Dec. 5, 2019, PCT No. PCT/US2019/064661
§ 371(c)(1), (2) Date Mar. 28, 2022,
PCT Pub. No. WO2021/112852, PCT Pub. Date Jun. 10, 2021.
Prior Publication US 2022/0335560 A1, Oct. 20, 2022
Int. Cl. G06T 1/00 (2006.01); G06N 3/045 (2023.01); G06T 3/4046 (2024.01); G06T 9/00 (2006.01)
CPC G06T 1/0057 (2013.01) [G06N 3/045 (2023.01); G06T 3/4046 (2013.01); G06T 9/002 (2013.01); G06T 2201/0083 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method to perform watermark-based image reconstruction to compensate for lossy encoding schemes, the method comprising:
obtaining, by one or more computing devices, an input image;
generating, by the one or more computing devices, a first output image by compressing and decompressing the input image according to a lossy compression scheme, wherein the first output image comprises a lossy reconstruction of the input image;
determining, by the one or more computing devices, a difference image that describes a difference between the input image and the first output image; and
processing, by the one or more computing devices, the difference image and the input image with a machine-learned message embedding model to generate a second output image as an output of the machine-learned message embedding model, wherein the second output image comprises an embedded message that is based at least in part on the difference image.