IMAGE WATERMARKING
    1.
    发明申请

    公开(公告)号:US20230111326A1

    公开(公告)日:2023-04-13

    申请号:US17792062

    申请日:2020-01-13

    申请人: GOOGLE LLC

    摘要: Methods, systems, and computer programs encoded on a computer storage medium, that relate to extracting digital watermarks from images, irrespective of distortions introduced into these images. Methods can include inputting a first data item into a channel encoder that can generate a first encoded data item that is greater in length than the first data item and that (1) includes the input data item and (2) new data this is redundant of the input data item. Based on the first encoded data item and a first image, an encoder model can generate a first encoded image into which the first encoded data is embedded as a digital watermark. A decoder model can decode the first encoded data item to generate a second data, which can be decoded by the channel decoder to generate data that is predicted to be the first data.

    Systems and Techniques for Retraining Models for Video Quality Assessment and for Transcoding Using the Retrained Models

    公开(公告)号:US20220415039A1

    公开(公告)日:2022-12-29

    申请号:US17762289

    申请日:2019-11-26

    申请人: Google LLC

    摘要: A trained model is retrained for video quality assessment and used to identify sets of adaptive compression parameters for transcoding user generated video content. Using transfer learning, the model, which is initially trained for image object detection, is retrained for technical content assessment and then again retrained for video quality assessment. The model is then deployed into a transcoding pipeline and used for transcoding an input video stream of user generated content. The transcoding pipeline may be structured in one of several ways. In one example, a secondary pathway for video content analysis using the model is introduced into the pipeline, which does not interfere with the ultimate output of the transcoding should there be a network or other issue. In another example, the model is introduced as a library within the existing pipeline, which would maintain a single pathway, but ultimately is not expected to introduce significant latency.

    GENERATING QUANTIZATION TABLES FOR IMAGE COMPRESSION

    公开(公告)号:US20230130410A1

    公开(公告)日:2023-04-27

    申请号:US17918170

    申请日:2020-04-17

    申请人: Google LLC

    IPC分类号: G06T9/00 G06T3/40

    摘要: Methods, systems, and computer programs encoded on a computer storage medium, that relate to generating quantization tables that are used during digital image compression of a digital image. Multiple training images are obtained. A model can be trained using the training images to generate a quantization table that can be used during encoding of an input image. For each training image, a quantization table can be obtained using the model. Using the quantization table, an encoded digital image is obtained for the training image. Using the encoded digital image and the training image, an image quality loss and a compression loss can be determined. An overall loss of the model can be determined by combining the image quality loss and the compression loss for the training image. The model can be updated based on the overall loss.

    Verification of the Authenticity of Images Using a Decoding Neural Network

    公开(公告)号:US20230061517A1

    公开(公告)日:2023-03-02

    申请号:US17789323

    申请日:2020-02-03

    申请人: Google LLC

    发明人: Feng Yang Hui Fang

    摘要: This document describes techniques and apparatuses for verifying the authenticity of images. In aspects, methods include receiving, by a decoder system (220), an image (210) to be verified; performing feature recognition on the received image to determine determined features (238) of the received image; generating a first output (236) defining values representing the determined features; decoding the received image, by a message decoding neural network (252), to extract a signature (254) embedded in the received image, the embedded signature representing recovered features (258) of the received image; generating a second output (256) defining values representing the recovered features; providing the first output and the second output to a manipulation detection neural network (272); and generating, by the manipulation detection neural network, an estimation of an authenticity of the received image utilizing at least the first output and the second output.

    EVALUATING VISUAL QUALITY OF DIGITAL CONTENT

    公开(公告)号:US20220301141A1

    公开(公告)日:2022-09-22

    申请号:US17612372

    申请日:2020-08-06

    申请人: GOOGLE LLC

    IPC分类号: G06T7/00 G06V10/82

    摘要: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include training machine learning models on images. A request is received to evaluate quality of an image included in a current version of a digital component generated by the computing device. The machine learning models are deployed on the image to generate a score for each quality characteristic of the image. A weight is assigned to each score to generate weighted scores. The weighted scores are combined to generate a combined score for the image. The combined score is compared to one or more thresholds to generate a quality of the image.

    Encoders for Improved Image Dithering

    公开(公告)号:US20210304445A1

    公开(公告)日:2021-09-30

    申请号:US16834857

    申请日:2020-03-30

    申请人: Google LLC

    摘要: Example embodiments allow for training of encoders (e.g., artificial neural networks (ANNs)) to facilitate dithering of images that have been subject to quantization in order to reduce the number of colors and/or size of the images. Such a trained encoder generates a dithering image from an input quantized image that can be combined, by addition or by some other process, with the quantized image to result in a dithered output image that exhibits reduced banding or is otherwise aesthetically improved relative to the un-dithered quantized image. The use of a trained encoder to facilitate dithering of quantized images allows the dithering to be performed in a known period of time using a known amount of memory, in contrast to alternative iterative dithering methods. Additionally, the trained encoder can be differentiable, allowing it to be part of a deep learning image processing pipeline or other machine learning pipeline.

    Debanding Using A Novel Banding Metric

    公开(公告)号:US20230131228A1

    公开(公告)日:2023-04-27

    申请号:US17922531

    申请日:2020-05-19

    申请人: Google LLC

    摘要: A method includes training a first model to measure the banding artefacts, training a second model to deband the image, and generating a debanded image for the image using the second model. Training the first model can include selecting a first set of first training images, generating a banding edge map for a first training image, where the map includes weights that emphasize banding edges and de-emphasize true edges in the first training image, and using the map and a luminance plane of the first training image as input to the first model. Training the second model can include selecting a second set of second training images, generating a debanded training image for a second training image, generating a banding score for the debanded training image using the first model, and using the banding score in a loss function used in training the second model.

    Watermark-Based Image Reconstruction

    公开(公告)号:US20220335560A1

    公开(公告)日:2022-10-20

    申请号:US17764445

    申请日:2019-05-12

    申请人: Google LLC

    摘要: 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.