中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

198 records (took 0.025 seconds)

    Few-shot digital image generation using gan-to-gan translation
    172.
    发明授权
    Few-shot digital image generation using gan-to-gan translation 有权

    公开(公告)号：US11763495B2

    公开(公告)日：2023-09-19

    申请号：US17163284

    申请日：2021-01-29

    Applicant: Adobe Inc.

    Inventor： Utkarsh Ojha ,  Yijun Li ,  Richard Zhang ,  Jingwan Lu ,  Elya Shechtman ,  Alexei A. Efros

    IPC: G06T11/00 ,  G06N3/02 ,  G06F18/22 ,  G06F18/214

    CPC classification number: G06T11/00 ,  G06F18/214 ,  G06F18/22 ,  G06N3/02

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently modifying a generative adversarial neural network using few-shot adaptation to generate digital images corresponding to a target domain while maintaining diversity of a source domain and realism of the target domain. In particular, the disclosed systems utilize a generative adversarial neural network with parameters learned from a large source domain. The disclosed systems preserve relative similarities and differences between digital images in the source domain using a cross-domain distance consistency loss. In addition, the disclosed systems utilize an anchor-based strategy to encourage different levels or measures of realism over digital images generated from latent vectors in different regions of a latent space.

    GENERATING MODIFIED DIGITAL IMAGES INCORPORATING SCENE LAYOUT UTILIZING A SWAPPING AUTOENCODER
    173.
    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.

    Incorporating black-box functions in neural networks
    177.
    发明授权
    Incorporating black-box functions in neural networks 有权

    公开(公告)号：US11481619B2

    公开(公告)日：2022-10-25

    申请号：US16507675

    申请日：2019-07-10

    Applicant: Adobe Inc.

    Inventor： Oliver Wang ,  Kevin Wampler ,  Kalyan Krishna Sunkavalli ,  Elya Shechtman ,  Siddhant Jain

    IPC: G06F17/13 ,  G06N3/08 ,  G06N3/10

    Abstract: Techniques for incorporating a black-box function into a neural network are described. For example, an image editing function may be the black-box function and may be wrapped into a layer of the neural network. A set of parameters and a source image are provided to the black-box function, and the output image that represents the source image with the set of parameters applied to the source image is output from the black-box function. To address the issue that the black-box function may not be differentiable, a loss optimization may calculate the gradients of the function using, for example, a finite differences calculation, and the gradients are used to train the neural network to ensure the output image is representative of an expected ground truth image.

    LOCAL NEURAL IMPLICIT FUNCTIONS WITH MODULATED PERIODIC ACTIVATIONS
    178.
    发明申请
    LOCAL NEURAL IMPLICIT FUNCTIONS WITH MODULATED PERIODIC ACTIVATIONS 有权

    公开(公告)号：US20220292341A1

    公开(公告)日：2022-09-15

    申请号：US17198670

    申请日：2021-03-11

    Applicant: ADOBE INC.

    Inventor： lshit bhadresh Mehta ,  Michaël Gharbi ,  Connelly Barnes ,  Elya Shechtman

    IPC: G06N3/08 ,  G06N3/04 ,  G06T5/00 ,  G06T3/40

    Abstract: Systems and methods for signal processing are described. Embodiments receive a digital signal comprising original signal values corresponding to a discrete set of original sample locations, generate modulation parameters based on the digital signal using a modulator network, wherein each of a plurality of modulator layers of the modulator network outputs a set of the modulation parameters, and generate a predicted signal value of the digital signal at an additional location using a synthesizer network, wherein each of a plurality of synthesizer layers of the synthesizer network operates based on the set of the modulation parameters from a corresponding modulator layer of the modulator network.

    Image composites using a generative neural network
    179.
    发明授权
    Image composites using a generative neural network 有权

    公开(公告)号：US11328523B2

    公开(公告)日：2022-05-10

    申请号：US16897068

    申请日：2020-06-09

    Applicant: Adobe Inc.

    Inventor： Elya Shechtman ,  Oliver Wang ,  Mehmet Yumer ,  Chen-Hsuan Lin

    IPC: G06V30/194 ,  G06N3/04 ,  G06N3/08

    Abstract: The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.

    ATTRIBUTE DECORRELATION TECHNIQUES FOR IMAGE EDITING
    180.
    发明申请
    ATTRIBUTE DECORRELATION TECHNIQUES FOR IMAGE EDITING 有权

    公开(公告)号：US20220122232A1

    公开(公告)日：2022-04-21

    申请号：US17468476

    申请日：2021-09-07

    Applicant: Adobe Inc.

    Inventor： Wei-An Lin ,  Baldo Faieta ,  Cameron Smith ,  Elya Shechtman ,  Jingwan Lu ,  Jun-Yan Zhu ,  Niloy Mitra ,  Ratheesh Kalarot ,  Richard Zhang ,  Shabnam Ghadar ,  Zhixin Shu

    IPC: G06T5/00 ,  G06T5/20 ,  G06N3/08

    Abstract: Systems and methods generate a filtering function for editing an image with reduced attribute correlation. An image editing system groups training data into bins according to a distribution of a target attribute. For each bin, the system samples a subset of the training data based on a pre-determined target distribution of a set of additional attributes in the training data. The system identifies a direction in the sampled training data corresponding to the distribution of the target attribute to generate a filtering vector for modifying the target attribute in an input image, obtains a latent space representation of an input image, applies the filtering vector to the latent space representation of the input image to generate a filtered latent space representation of the input image, and provides the filtered latent space representation as input to a neural network to generate an output image with a modification to the target attribute.

Patent Agency Ranking