知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

29 records (took 0.022 seconds)

    GENERATIVE ADVERSARIAL NETWORK MANIPULATED IMAGE EFFECTS
    16.
    发明申请
    GENERATIVE ADVERSARIAL NETWORK MANIPULATED IMAGE EFFECTS 有权

    公开(公告)号：US20220207355A1

    公开(公告)日：2022-06-30

    申请号：US17318658

    申请日：2021-05-12

    Applicant: Snap Inc.

    Inventor： Sergey Demyanov ,  Konstantin Gudkov ,  Aleksei Stoliar ,  Roman Ushakov ,  Fedor Zhdanov

    IPC: G06N3/08 ,  G06N3/04 ,  G06T11/60

    Abstract: Systems and methods herein describe an image manipulation system for generating modified images using a generative adversarial network. The image manipulation system accesses a pre-trained generative adversarial network (GAN), fine-tunes the pre-trained GAN by training a portion of existing neural network layers of the pre-trained GAN and newly added layers of the pre-trained GAN on a secondary image domain, adjusts the weights of the fine-tuned GAN using the weights of the pre-trained GAN, and stores the fine-tuned GAN. An image transformation system uses the generated modified images to train a subsequent neural network, which can access a face from a client device and transform it to a domain of images used for GAN fine-tuning.

    Domain changes in generative adversarial networks
    17.
    发明授权
    Domain changes in generative adversarial networks 有权

    公开(公告)号：US12148202B2

    公开(公告)日：2024-11-19

    申请号：US17841333

    申请日：2022-06-15

    Applicant: Snap Inc.

    Inventor： Sergey Demyanov ,  Konstantin Gudkov ,  Fedor Zhdanov ,  Andrei Zharkov

    IPC: G06T11/00 ,  G06T3/18 ,  G06T7/68 ,  G06V10/74 ,  G06V10/774 ,  G06V10/82 ,  G06V40/16

    Abstract: An image manipulation system for generating modified images using a generative adversarial network (GAN) trains GANs using domain changes, aligns input images with generated images, classifies and associates target images based on a symmetry, and uses a modified discriminator structure. A method for domain changes includes generating, using a pre-trained GAN trained on a plurality of first target images, a plurality of images, and determining a feature for each of the plurality of images. The method further includes determining the feature for each of a plurality of second target images and matching, based on the feature, second target images of the plurality of second target images with the plurality of images. The method further includes training a discriminator of the pre-trained GAN with the second target images and the plurality of images.

Patent Agency Ranking