中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

3 records (took 0.01 seconds)

    REAR CONVERTER
    1.
    发明申请
    REAR CONVERTER 有权
    后转换器

    公开(公告)号：US20150248050A1

    公开(公告)日：2015-09-03

    申请号：US14627173

    申请日：2015-02-20

    Applicant: SONY CORPORATION

    Inventor： AKIRA NAKAMURA

    IPC: G03B17/56 ,  G02B15/10 ,  G03B13/32

    CPC classification number: G03B17/565 ,  G02B9/02 ,  G02B9/04 ,  G02B9/12 ,  G02B13/0035 ,  G02B15/04 ,  G02B15/10 ,  G03B17/48

    Abstract: There is provided rear converter including a first lens that is a negative lens of which both surfaces are concave, a second lens that is a negative lens of which both an image plane side and an object side are convex toward an object side, and a third lens that is a positive lens of which both sides are convex. The first to third lenses are disposed in this order from the object side, and the rear converter is inserted and used between an imaging lens and a camera.

    Abstract translation: 提供了后转换器，其包括作为其两个表面都是凹的负透镜的第一透镜，作为物镜侧朝向物侧的凸面侧的负透镜的第二透镜，以及第三透镜 透镜是两侧凸起的正透镜。 第一至第三透镜从物体侧按此顺序设置，并且后转换器插入并在成像透镜和照相机之间使用。

    IMAGE COMPONENT GENERATION BASED ON APPLICATION OF ITERATIVE LEARNING ON AUTOENCODER MODEL AND TRANSFORMER MODEL
    2.
    发明公开
    IMAGE COMPONENT GENERATION BASED ON APPLICATION OF ITERATIVE LEARNING ON AUTOENCODER MODEL AND TRANSFORMER MODEL 审中-公开

    公开(公告)号：US20240029411A1

    公开(公告)日：2024-01-25

    申请号：US18177084

    申请日：2023-03-01

    Applicant: SONY GROUP CORPORATION ,  SONY CORPORATION OF AMERICA

    Inventor： MARZIEH EDRAKI ,  AKIRA NAKAMURA

    IPC: G06V10/774 ,  G06V10/82

    CPC classification number: G06V10/774 ,  G06V10/82

    Abstract: An electronic device and method for image component generation based on application of iterative learning on autoencoder model and transformer model is provided. The electronic device fine-tunes, based on first training data including a first set of images, an autoencoder model and a transformer model. The autoencoder model includes an encoder model, a learned codebook, a generator model, and a discriminator model. The electronic device selects a subset of images from the first training data. The electronic device applies the encoder model on the selected subset of images. The electronic device generates second training data including a second set of images, based on the application of the encoder model. The generated second training data corresponds to a quantized latent representation of the selected subset of images. The electronic device pre-trains the autoencoder model to create a next generation of the autoencoder model, based on the generated second training data.

Patent Agency Ranking