Watermark-based image reconstruction
AssigneeGoogle Inc.
InventorsInnfarn Yoo, Feng Yang, Xiyang Luo
Life of this patent
Estimating the term…
Abstract
A computer-implemented method that provides watermark-based image reconstruction to compensate for lossy encoding schemes. The method can generate a difference image describing the data loss associated with encoding an image using a lossy encoding scheme. The difference image can be encoded as a message and embedded in the encoded image using a watermark and later extracted from the encoded image. The difference image can be added to the encoded image to reconstruct the original image. As an example, an input image encoded using a lossy JPEG compression scheme can be embedded with the lost data and later reconstructed, using the embedded data, to a fidelity level that is identical or substantially similar to the original.
Claims22
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.
A computing system comprising:
- one or more processors;
- and
- a first set of instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
- obtaining an input image;
- encoding and decoding the input image according to an encoding scheme to generate a first output image;
- determining a difference image that describes a difference between the input image and the first output image;
- generating, using a machine-learned message embedding model, a second output image that comprises an embedded message generated by the machine-learned message embedding model based at least in part on the difference image;
- using a machine-learned message extraction model to extract the embedded message from the second output image to obtain a reconstruction of the difference image;
- evaluating a loss function that evaluates a difference between the input image and the reconstruction of the input image;
- and
- modifying values for one or more parameters of at least the machine-learned message extraction model based on the loss function.
One or more non-transitory computer-readable media that store instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations comprising:
- obtaining an encoded version of an image that contains an embedded message;
- decoding the encoded version of the image to obtain a decoded version of the image;
- extracting, using a machine-learned message extraction model, the embedded message from the decoded version of the image to obtain a reconstruction of a difference image that describes a difference between an input image and an output image generated through application of an encoding and decoding scheme to the input image;
- and
- generating a reconstruction of the input image based at least in part on the decoded version of the image and the reconstruction of the difference image.
Dependencies are inferred from the claim text.