中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.014 seconds)

    Pose prediction with recurrent neural networks
    2.
    发明授权
    Pose prediction with recurrent neural networks 有权

    公开(公告)号：US10989916B2

    公开(公告)日：2021-04-27

    申请号：US16545803

    申请日：2019-08-20

    Applicant: Google LLC

    Inventor： Ivana Tosic Rodgers ,  David Chu ,  Mohammad Moharrami ,  Sebastian Sylvan

    IPC: G02B27/00 ,  G02B27/01 ,  G06N3/04 ,  G06T19/00

    Abstract: Systems, methods, and computer program products are described for receiving a request for a head pose prediction for an augmented reality experience, identifying at least one positional indicator and at least one rotational indicator associated with the augmented reality experience, and providing the at least one positional indicator and the at least one rotational indicator to a Recurrent Neural Network (RNN) comprising a plurality of cells. The RNN may include a plurality of recurrent steps that each include at least one of the plurality of cells and at least one fully connected (FC) layer. The RNN may be used to generate at least one pose prediction corresponding to head pose changes for the augmented reality experience for at least one upcoming time period, provide the at least one pose prediction and trigger display of augmented reality content based on the at least one pose prediction.

    POSE PREDICTION WITH RECURRENT NEURAL NETWORKS
    3.
    发明申请
    POSE PREDICTION WITH RECURRENT NEURAL NETWORKS 有权

    公开(公告)号：US20210055545A1

    公开(公告)日：2021-02-25

    申请号：US16545803

    申请日：2019-08-20

    Applicant: Google LLC

    Inventor： Ivana Tosic Rodgers ,  David Chu ,  Mohammad Moharrami ,  Sebastian Sylvan

    IPC: G02B27/00 ,  G06T19/00 ,  G06N3/04 ,  G02B27/01

    Abstract: Systems, methods, and computer program products are described for receiving a request for a head pose prediction for an augmented reality experience, identifying at least one positional indicator and at least one rotational indicator associated with the augmented reality experience, and providing the at least one positional indicator and the at least one rotational indicator to a Recurrent Neural Network (RNN) comprising a plurality of cells. The RNN may include a plurality of recurrent steps that each include at least one of the plurality of cells and at least one fully connected (FC) layer. The RNN may be used to generate at least one pose prediction corresponding to head pose changes for the augmented reality experience for at least one upcoming time period, provide the at least one pose prediction and trigger display of augmented reality content based on the at least one pose prediction.

    Adaptive Mesh Reprojection for Low Latency 6DOF Rendering
    4.
    发明申请
    Adaptive Mesh Reprojection for Low Latency 6DOF Rendering 有权

    公开(公告)号：US20230134779A1

    公开(公告)日：2023-05-04

    申请号：US18050058

    申请日：2022-10-27

    Applicant: Google LLC

    Inventor： Bernhard Reinert ,  Sebastian Sylvan ,  Hugues Hoppe ,  Grigory Javadyan ,  Egor Yusov ,  David Chu ,  Kelvin Ritland

    IPC: G06T17/20 ,  G06T7/50 ,  G06V10/74

    Abstract: A method includes obtaining a first frame of image data including a plurality of pixels. Each pixel of the plurality of pixels is associated with a respective color value and a respective depth value. The first frame renders a scene from a first point of view. The method includes generating a three-dimensional (3D) polygon mesh using the plurality of pixels and the respective depth values. The 3D polygon mesh includes a plurality of portions. Each respective portion defines a respective plurality of vertices defining a respective mesh density representative of a density of the respective plurality of vertices. Each vertex is associated with a corresponding pixel of the first frame of image data. The method includes generating a second frame of image data via reprojection using the generated 3D polygon mesh. The second frame of image data has a second point of view different from the first point of view.

    CONGESTION CONTROL FOR LOW-LATENCY INTERACTIVE VIDEO STREAMING
    5.
    发明申请
    CONGESTION CONTROL FOR LOW-LATENCY INTERACTIVE VIDEO STREAMING 有权

    公开(公告)号：US20250039099A1

    公开(公告)日：2025-01-30

    申请号：US18790035

    申请日：2024-07-31

    Applicant: GOOGLE LLC

    Inventor： Teng Wei ,  Connor Smith ,  David Chu ,  Devdeep Ray ,  Bernhard Reinert ,  Zengbin Zhang

    IPC: H04L47/2416 ,  A63F13/355 ,  H04L47/12 ,  H04L65/61

    Abstract: A server transmits an encoded game frame over a network to a respective client system as a set of packets. In response to transmitting the set of packets, the server determines a bandwidth estimate based on the size of the encoded game frame and the timing data associated with the transmitted set of packets. The server then compares the bandwidth estimate to a current video bitrate of the game stream being transmitted from the server to the respective client device. In response to the comparison indicating an underutilization of the network, the server increases the encoding bitrate. Further, in response to the comparison indication an overutilization of the network, the server decreases the encoding bitrate.

Patent Agency Ranking