中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

19 records (took 0.019 seconds)

    Projecting Images To A Generative Model Based On Gradient-free Latent Vector Determination
    2.
    发明申请
    Projecting Images To A Generative Model Based On Gradient-free Latent Vector Determination 有权

    公开(公告)号：US20220414431A1

    公开(公告)日：2022-12-29

    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.

    MODIFYING NEURAL NETWORKS FOR SYNTHETIC CONDITIONAL DIGITAL CONTENT GENERATION UTILIZING CONTRASTIVE PERCEPTUAL LOSS
    3.
    发明申请
    MODIFYING NEURAL NETWORKS FOR SYNTHETIC CONDITIONAL DIGITAL CONTENT GENERATION UTILIZING CONTRASTIVE PERCEPTUAL LOSS 有权

    公开(公告)号：US20220148242A1

    公开(公告)日：2022-05-12

    申请号：US17091440

    申请日：2020-11-06

    Applicant: Adobe Inc.

    Inventor： Bryan Russell ,  Taesung Park ,  Richard Zhang ,  Junyan Zhu ,  Alexander Andonian

    IPC: G06T11/60 ,  G06N3/04

    Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize a contrastive perceptual loss to modify neural networks for generating synthetic digital content items. For example, the disclosed systems generate a synthetic digital content item based on a guide input to a generative neural network. The disclosed systems utilize an encoder neural network to generate encoded representations of the synthetic digital content item and a corresponding ground-truth digital content item. Additionally, the disclosed systems sample patches from the encoded representations of the encoded digital content items and then determine a contrastive loss based on the perceptual distances between the patches in the encoded representations. Furthermore, the disclosed systems jointly update the parameters of the generative neural network and the encoder neural network utilizing the contrastive loss.

    Projecting images to a generative model based on gradient-free latent vector determination
    5.
    发明授权
    Projecting images to a generative model based on gradient-free latent vector determination 有权

    公开(公告)号：US11468294B2

    公开(公告)日：2022-10-11

    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 ,  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.

    Generating modified digital images incorporating scene layout utilizing a swapping autoencoder
    6.
    发明授权
    Generating modified digital images incorporating scene layout utilizing a swapping autoencoder 有权

    公开(公告)号：US12254545B2

    公开(公告)日：2025-03-18

    申请号：US18298138

    申请日：2023-04-10

    Applicant: Adobe Inc.

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

    IPC: G06T11/60 ,  G06N3/045 ,  G06N3/088 ,  G06T7/10

    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
    8.
    发明公开
    GENERATING MODIFIED DIGITAL IMAGES INCORPORATING SCENE LAYOUT UTILIZING A SWAPPING AUTOENCODER 审中-公开

    公开(公告)号：US20230245363A1

    公开(公告)日：2023-08-03

    申请号：US18298138

    申请日：2023-04-10

    Applicant: Adobe Inc.

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

    IPC: G06T11/60 ,  G06N3/088 ,  G06T7/10 ,  G06N3/045

    CPC classification number: G06T11/60 ,  G06N3/088 ,  G06T7/10 ,  G06N3/045

    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.

    Modifying neural networks for synthetic conditional digital content generation utilizing contrastive perceptual loss
    10.
    发明授权
    Modifying neural networks for synthetic conditional digital content generation utilizing contrastive perceptual loss 有权

    公开(公告)号：US11514632B2

    公开(公告)日：2022-11-29

    申请号：US17091440

    申请日：2020-11-06

    Applicant: Adobe Inc.

    Inventor： Bryan Russell ,  Taesung Park ,  Richard Zhang ,  Junyan Zhu ,  Alexander Andonian

    IPC: G09G5/00 ,  G06T11/60 ,  G06N3/04

    Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize a contrastive perceptual loss to modify neural networks for generating synthetic digital content items. For example, the disclosed systems generate a synthetic digital content item based on a guide input to a generative neural network. The disclosed systems utilize an encoder neural network to generate encoded representations of the synthetic digital content item and a corresponding ground-truth digital content item. Additionally, the disclosed systems sample patches from the encoded representations of the encoded digital content items and then determine a contrastive loss based on the perceptual distances between the patches in the encoded representations. Furthermore, the disclosed systems jointly update the parameters of the generative neural network and the encoder neural network utilizing the contrastive loss.

Patent Agency Ranking