中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.019 seconds)

    Image enhancement via iterative refinement based on machine learning models
    1.
    发明授权
    Image enhancement via iterative refinement based on machine learning models 有权

    公开(公告)号：US12165289B2

    公开(公告)日：2024-12-10

    申请号：US18227120

    申请日：2023-07-27

    Applicant: Google LLC

    Inventor： Chitwan Saharia ,  Jonathan Ho ,  William Chan ,  Tim Salimans ,  David Fleet ,  Mohammad Norouzi

    IPC: G06T5/70 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4007 ,  G06T5/50

    Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

    GENERATING VIDEOS USING DIFFUSION MODELS
    2.
    发明公开
    GENERATING VIDEOS USING DIFFUSION MODELS 审中-公开

    公开(公告)号：US20240338936A1

    公开(公告)日：2024-10-10

    申请号：US18296938

    申请日：2023-04-06

    Applicant: Google LLC

    Inventor： Jonathan Ho ,  Tim Salimans ,  Alexey Alexeevich Gritsenko ,  William Chan ,  Mohammad Norouzi ,  David James Fleet

    IPC: G06V10/82 ,  G06V10/771 ,  H04N7/01

    CPC classification number: G06V10/82 ,  G06V10/771 ,  H04N7/0117 ,  H04N7/013

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output video conditioned on an input. In one aspect, a method comprises receiving the input; initializing a current intermediate representation; generating an output video by updating the current intermediate representation at each of a plurality of iterations, wherein the updating comprises, at each iteration: processing an intermediate input for the iteration comprising the current intermediate representation using a diffusion model that is configured to process the intermediate input to generate a noise output; and updating the current intermediate representation using the noise output for the iteration.

    Image Enhancement via Iterative Refinement based on Machine Learning Models
    6.
    发明申请
    Image Enhancement via Iterative Refinement based on Machine Learning Models 有权

    公开(公告)号：US20250061551A1

    公开(公告)日：2025-02-20

    申请号：US18939994

    申请日：2024-11-07

    Applicant: Google LLC

    Inventor： Chitwan Saharia ,  Jonathan Ho ,  William Chan ,  Tim Salimans ,  David Fleet ,  Mohammad Norouzi

    IPC: G06T5/70 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4007 ,  G06T5/50

    Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

    Diffusion Models Having Improved Accuracy and Reduced Consumption of Computational Resources
    7.
    发明公开
    Diffusion Models Having Improved Accuracy and Reduced Consumption of Computational Resources 审中-公开

    公开(公告)号：US20230267315A1

    公开(公告)日：2023-08-24

    申请号：US18012195

    申请日：2022-06-13

    Applicant: Google LLC

    Inventor： Diederik Pieter Kingma ,  Tim Salimans

    IPC: G06N3/048

    CPC classification number: G06N3/048

    Abstract: A computer-implemented method for use of a diffusion model having improved accuracy comprises obtaining input data, the input data comprising one or more channels; providing the input data to a machine-learned diffusion model, the machine-learned diffusion model comprising: a noising model comprising a plurality of noising stages, the noising model configured to introduce noise to receive the input data and produce intermediate data in response to receipt of the input data; and a denoising model configured to reconstruct output data from the intermediate data; and receiving, by the computing system, the output data from the machine-learned diffusion model. The diffusion model can include a learned noise schedule. Additionally and/or alternatively, input to the denoising model can include a set of Fourier features. Additionally and/or alternatively, the diffusion model can be trained based at least in part on a continuous-time loss for an evidence lower bound.

Patent Agency Ranking