中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.02 seconds)

    NEURAL NETWORKS TO GENERATE OBJECTS WITHIN DIFFERENT IMAGES
    2.
    发明申请
    NEURAL NETWORKS TO GENERATE OBJECTS WITHIN DIFFERENT IMAGES 有权

    公开(公告)号：US20250166237A1

    公开(公告)日：2025-05-22

    申请号：US18518430

    申请日：2023-11-22

    Applicant: NVIDIA Corporation

    Inventor： Yu Zeng ,  Yogesh Balaji ,  Ting-Chun Wang ,  Xun Huang ,  Ming-Yu Liu

    IPC: G06T11/00 ,  G06T5/00 ,  G06T7/70

    Abstract: Apparatuses, processors, computing systems, devices, non-transitory computer medium, and/or methods for using neural networks for generating multiple related images. In at least one embodiment, a processor includes circuitry to use one or more neural networks to generate several images, where each image includes a same object (e.g., same subject) and different backgrounds. For example, a processor including one or more circuits to use one or more neural networks to generate one or more objects (e.g., an animal, a vehicle, a person) within two or more different images (e.g., different backgrounds such as weather, season, environment) based, at least in part, on one or more indications (e.g., text prompts) by one or more users indicating content of at least one of the two or more different images (e.g., objects and/or backgrounds for each image in text such as adjectives and nouns) other than the one or more objects.

    IMAGE SYNTHESIS USING ONE OR MORE NEURAL NETWORKS
    6.
    发明申请
    IMAGE SYNTHESIS USING ONE OR MORE NEURAL NETWORKS 有权

    公开(公告)号：US20220237838A1

    公开(公告)日：2022-07-28

    申请号：US17159977

    申请日：2021-01-27

    Applicant: Nvidia Corporation

    Inventor： Ming-Yu Liu ,  Xun Huang

    IPC: G06T11/60 ,  G06N3/04

    Abstract: Apparatuses, systems, and techniques are presented to synthesize representations. In at least one embodiment, one or more neural networks are used to generate one or more representations of one or more objects based, at least in part, upon one or more structural features and one or more appearance features for the one or more objects.

    METHOD FOR FEW-SHOT UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION
    8.
    发明申请
    METHOD FOR FEW-SHOT UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION 审中-公开

    公开(公告)号：US20200242736A1

    公开(公告)日：2020-07-30

    申请号：US16261395

    申请日：2019-01-29

    Applicant: Nvidia Corporation

    Inventor： Ming-Yu Liu ,  Xun Huang ,  Tero Karras ,  Timo Aila ,  Jaakko Lehtinen

    IPC: G06T3/60 ,  G06T3/00 ,  G06K9/62 ,  G06T7/73

    Abstract: A few-shot, unsupervised image-to-image translation (“FUNIT”) algorithm is disclosed that accepts as input images of previously-unseen target classes. These target classes are specified at inference time by only a few images, such as a single image or a pair of images, of an object of the target type. A FUNIT network can be trained using a data set containing images of many different object classes, in order to translate images from one class to another class by leveraging few input images of the target class. By learning to extract appearance patterns from the few input images for the translation task, the network learns a generalizable appearance pattern extractor that can be applied to images of unseen classes at translation time for a few-shot image-to-image translation task.

    MULTI-MODAL IMAGE TRANSLATION USING NEURAL NETWORKS
    9.
    发明申请
    MULTI-MODAL IMAGE TRANSLATION USING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20190279075A1

    公开(公告)日：2019-09-12

    申请号：US16279671

    申请日：2019-02-19

    Applicant: Nvidia Corporation

    Inventor： Ming-Yu Liu ,  Xun Huang

    IPC: G06N3/04 ,  G06N5/04 ,  G06F17/18 ,  G06T3/00

    Abstract: A source image is processed using an encoder network to determine a content code representative of a visual aspect of the source object represented in the source image. A target class is determined, which can correspond to an entire population of objects of a particular type. The user may specify specific objects within the target class, or a sampling can be done to select objects within the target class to use for the translation. Style codes for the selected target objects are determined that are representative of the appearance of those target objects. The target style codes are provided with the source content code as input to a translation network, which can use the codes to infer a set of images including representations of the selected target objects having the visual aspect determined from the source image.

Patent Agency Ranking