利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

272 条记录 (耗时 0.02 秒)

    JAW MOVEMENTS DATA GENERATION APPARATUS, DATA GENERATION METHOD, AND DATA GENERATION PROGRAM
    2.
    发明公开
    JAW MOVEMENTS DATA GENERATION APPARATUS, DATA GENERATION METHOD, AND DATA GENERATION PROGRAM 审中-公开

    公开(公告)号：EP4328861A2

    公开(公告)日：2024-02-28

    申请号：EP23192143.8

    申请日：2023-08-18

    申请人： J. MORITA MANUFACTURING CORPORATION

    发明人： YOSHIKAWA, Hideki ,  NISHIMURA, Yuu

    IPC分类号： G06T13/20

    摘要： A data generation apparatus (10) includes a moving image data interface (13) and a three-dimensional data interface (14) to which moving image data obtained by photographing a subject making a jaw movement with a partial teeth row of an upper and/or lower teeth row exposed and three-dimensional data of the upper and/or lower teeth row of the subject are input respectively, and an arithmetic device (11) configured to generate jaw movement-related data related to the jaw movement of the subject based on the partial teeth row included in each of a plurality of frame images constituting the moving image data and the three-dimensional data of the upper and/or lower teeth row.

    METHOD AND APPARATUS OF PROCESSING IMAGE, METHOD AND APPARATUS OF TRAINING MODEL, ELECTRONIC DEVICE AND MEDIUM
    5.
    发明公开
    METHOD AND APPARATUS OF PROCESSING IMAGE, METHOD AND APPARATUS OF TRAINING MODEL, ELECTRONIC DEVICE AND MEDIUM 审中-公开

    公开(公告)号：EP4177884A1

    公开(公告)日：2023-05-10

    申请号：EP22206073.3

    申请日：2022-11-08

    申请人： Beijing Baidu Netcom Science Technology Co., Ltd.

    发明人： Hu, Tianshu ,  He, Shengyi ,  Han, Junyu ,  Hong, Zhibin

    IPC分类号： G10L21/10 ,  G06T13/20

    摘要： The present disclosure provides a method and apparatus of processing an image, a method and apparatus of training a model, an electronic device and a medium, which relate to a field of artificial intelligence technology, in particular to deep learning, computer vision and other technical fields. The specific solution includes: generating a first face image, a definition difference and an authenticity difference between the first face image and a reference face image are within a set range; adjusting, according to a target voice used to drive the first face image, a facial action information related to pronunciation in the first face image to generate a second face image with a facial tissue position conforming to a pronunciation rule of the target voice; and determining the second face image as a face image driven by the target voice. The embodiments of the present disclosure may improve an effect of face driving.

    IMAGE PROCESSING METHOD AND DEVICE, SERVER, AND MEDIUM
    8.
    发明公开
    IMAGE PROCESSING METHOD AND DEVICE, SERVER, AND MEDIUM 审中-公开

    公开(公告)号：EP4095804A1

    公开(公告)日：2022-11-30

    申请号：EP21853530.0

    申请日：2021-06-09

    申请人： Tencent Technology (Shenzhen) Company Limited

    发明人： ZHAO, Xinda ,  XU, Minhua ,  GONG, Zhipeng

    IPC分类号： G06T13/20

    摘要： An image processing method and device, a server, and a medium are provided. The method is implemented by a server, and comprises: when a target cloud game is running, acquiring feedback data sent by a target game client (S201), the feedback data being used to reflect a frame rate requirement of the target game client; dynamically adjusting an encoding frame rate according to the feedback data, so as to obtain an adjusted encoding frame rate (S202); performing image encoding on a game image of the target cloud game according to the adjusted encoding frame rate, so as to obtain encoded data (S203); and transmitting the encoded data to the target game client, such that the target game client displays the game image according to the encoded data (S204).