知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

19 records (took 0.015 seconds)

    Projecting Images To A Generative Model Based On Gradient-free Latent Vector Determination
    11.
    发明申请
    Projecting Images To A Generative Model Based On Gradient-free Latent Vector Determination 有权

    公开(公告)号：US20210264235A1

    公开(公告)日：2021-08-26

    申请号：US16798271

    申请日：2020-02-21

    Applicant: Adobe Inc.

    Inventor： Richard Zhang ,  Sylvain Philippe Paris ,  Junyan Zhu ,  Aaron Phillip Hertzmann ,  Jacob Minyoung Huh

    IPC: G06N3/04 ,  G06F17/18 ,  G06T11/60

    Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

    SUPER-RESOLUTION ON TEXT-TO-IMAGE SYNTHESIS WITH GANS
    12.
    发明公开
    SUPER-RESOLUTION ON TEXT-TO-IMAGE SYNTHESIS WITH GANS 审中-公开

    公开(公告)号：US20240281924A1

    公开(公告)日：2024-08-22

    申请号：US18171046

    申请日：2023-02-17

    Applicant: ADOBE INC.

    Inventor： Taesung Park ,  Minguk Kang ,  Richard Zhang ,  Junyan Zhu ,  Elya Shechtman ,  Sylvain Paris

    IPC: G06T3/40

    CPC classification number: G06T3/4046 ,  G06T3/4053

    Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure obtain a low-resolution image and a text description of the low-resolution image. A mapping network generates a style vector representing the text description of the low-resolution image. An adaptive convolution component generates an adaptive convolution filter based on the style vector. An image generation network generates a high-resolution image corresponding to the low-resolution image based on the adaptive convolution filter.

    Generating modified digital images incorporating scene layout utilizing a swapping autoencoder
    14.
    发明授权
    Generating modified digital images incorporating scene layout utilizing a swapping autoencoder 有权

    公开(公告)号：US11625875B2

    公开(公告)日：2023-04-11

    申请号：US17091416

    申请日：2020-11-06

    Applicant: Adobe Inc.

    Inventor： Taesung Park ,  Alexei A. Efros ,  Elya Shechtman ,  Richard Zhang ,  Junyan Zhu

    IPC: G06T11/60 ,  G06T7/10 ,  G06N3/088 ,  G06N3/04

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

    GENERATING MODIFIED DIGITAL IMAGES INCORPORATING SCENE LAYOUT UTILIZING A SWAPPING AUTOENCODER
    15.
    发明申请
    GENERATING MODIFIED DIGITAL IMAGES INCORPORATING SCENE LAYOUT UTILIZING A SWAPPING AUTOENCODER 有权

    公开(公告)号：US20220148241A1

    公开(公告)日：2022-05-12

    申请号：US17091416

    申请日：2020-11-06

    Applicant: Adobe Inc.

    Inventor： Taesung Park ,  Alexei A. Efros ,  Elya Shechtman ,  Richard Zhang ,  Junyan Zhu

    IPC: G06T11/60 ,  G06N3/04 ,  G06T7/10 ,  G06N3/08

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

    DATA ATTRIBUTION FOR DIFFUSION MODELS
    16.
    发明申请
    DATA ATTRIBUTION FOR DIFFUSION MODELS 有权

    公开(公告)号：US20250104399A1

    公开(公告)日：2025-03-27

    申请号：US18473603

    申请日：2023-09-25

    Applicant: ADOBE INC.

    Inventor： Sheng-Yu Wang ,  Alexei A. Efros ,  Junyan Zhu ,  Richard Zhang

    IPC: G06V10/77 ,  G06N3/0895 ,  G06V10/74 ,  G06V10/774 ,  G06V10/82

    Abstract: Embodiments of the present disclosure perform training attribution by identifying a synthesized image and a training image, where the synthesized image was generated by an image generation model that was trained with the training image. A machine learning model computes first attribution features for the synthesized image using a first mapping layer and second attribution features for the training image using a second mapping layer that is different from the first mapping layer. Then, an attribution score is generated based on the first attribution features and the second attribution features, where the attribution score indicates a degree of influence for the training image on generating the synthesized image.

    Projecting images to a generative model based on gradient-free latent vector determination
    18.
    发明授权
    Projecting images to a generative model based on gradient-free latent vector determination 有权

    公开(公告)号：US11615292B2

    公开(公告)日：2023-03-28

    申请号：US17899936

    申请日：2022-08-31

    Applicant: Adobe Inc.

    Inventor： Richard Zhang ,  Sylvain Philippe Paris ,  Junyan Zhu ,  Aaron Phillip Hertzmann ,  Jacob Minyoung Huh

    IPC: G06N3/04 ,  G06T11/60 ,  G06F17/18

    Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Patent Agency Ranking