知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.016 seconds)

    NEURAL NETWORK POWERED CODEC
    1.
    发明申请
    NEURAL NETWORK POWERED CODEC 有权

    公开(公告)号：US20210297695A1

    公开(公告)日：2021-09-23

    申请号：US17341825

    申请日：2021-06-08

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Jason N. Wang ,  Eric Hsuming Chen

    IPC: H04N19/593 ,  H04N19/436 ,  H04L29/06 ,  H04N19/563 ,  H04N19/107 ,  H04N19/523

    Abstract: Training a video decoder system may include masking one of at least two sets of video encoding parameters with invalid values to generate an invalid set. The at least two sets of video encoding parameters are provided to one or more neural networks to train them to predict valid values that correspond to values of the invalid set using an iterative training algorithm. Encoding parameters to encode are determined based on a prediction error of the one or more neural networks. Encoding parameters which are determined to be accurately predicted are dropped from the encoded data. A new video stream is encoded without the dropped encoding parameters.

    Neural network powered codec
    3.
    发明授权
    Neural network powered codec 有权

    公开(公告)号：US11432008B2

    公开(公告)日：2022-08-30

    申请号：US17341825

    申请日：2021-06-08

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Jason N. Wang ,  Eric Hsuming Chen

    IPC: H04N19/593 ,  H04N19/436 ,  H04N19/563 ,  H04N19/107 ,  H04N19/523 ,  H04L65/70

    Abstract: Training a video decoder system may include masking one of at least two sets of video encoding parameters with invalid values to generate an invalid set. The at least two sets of video encoding parameters are provided to one or more neural networks to train them to predict valid values that correspond to values of the invalid set using an iterative training algorithm. Encoding parameters to encode are determined based on a prediction error of the one or more neural networks. Encoding parameters which are determined to be accurately predicted are dropped from the encoded data. A new video stream is encoded without the dropped encoding parameters.

    REDUCING LATENCY IN NETWORKED GAMING BY REDUCING I-FRAME SIZES
    4.
    发明申请
    REDUCING LATENCY IN NETWORKED GAMING BY REDUCING I-FRAME SIZES 有权

    公开(公告)号：US20250108291A1

    公开(公告)日：2025-04-03

    申请号：US18478174

    申请日：2023-09-29

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Rathish Krishnan ,  Eric Hsuming Chen ,  Jason Wang ,  Deepali Arya ,  Hung-Ju Lee

    IPC: A63F13/335

    Abstract: Techniques are described for reducing latency in networked gaming by reducing I-frame sizes (which also results in automatically increasing P-frame sizes) to reduce the overall amount of video being transmitted. The reduced size of the I-frames is compensated for by increasing the size of other frames using a low pass filter (LPF) such as a Gaussian filter which reduces sharpness that the decoder can try to recover, or by use of lower resolution. The I-frame can be reduced by rotating it or flipping/mirroring it to produce the smaller coded frame, sending a flag to signal the orientation.

    NEURAL NETWORK POWERED CODEC
    6.
    发明申请
    NEURAL NETWORK POWERED CODEC 审中-公开

    公开(公告)号：US20190387252A1

    公开(公告)日：2019-12-19

    申请号：US16012570

    申请日：2018-06-19

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Jason N. Wang ,  Eric Hsuming Chen

    IPC: H04N19/593 ,  H04N19/436 ,  H04N19/523 ,  H04N19/563 ,  H04N19/107 ,  H04L29/06

    Abstract: Training a video decoder system comprising, generating at least two sets of video encoding parameters wherein the at least two sets of video encoding parameters are valid, masking a set of the at least two sets of encoding parameters with invalid values to generate an invalid set of video encoding parameters, providing a set of the at least two sets of video encoding parameters to a neural network, training the neural network to predict valid video encoding parameter values for the invalid set using an iterative training algorithm, determining which encoding parameters need to be encoded based on analysis of a prediction error of the trained recurrent neural network, dropping the encoding parameters from the encoded data which are determined to be accurately predicted by the trained recurrent neural network, encoding a new video stream without the dropped encoding parameters. A coder and decoder system with neural network is also disclosed.

    Neural network powered codec
    8.
    发明授权
    Neural network powered codec 有权

    公开(公告)号：US11032569B2

    公开(公告)日：2021-06-08

    申请号：US16684279

    申请日：2019-11-14

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Jason N. Wang ,  Eric Hsuming Chen

    IPC: H04N19/593 ,  H04N19/436 ,  H04N19/563 ,  H04N19/107 ,  H04N19/523 ,  H04L29/06

    Abstract: Training a video decoder system may include generating at least two valid sets of video encoding parameters and masking one of the sets with invalid values to generate an invalid set. The valid sets of video encoding parameters may be provided to one or more neural networks to train them to predict valid values that correspond to values of the invalid set using an iterative training algorithm. A prediction error of the predicted valid values is determined from the results of the training of the neural networks and the valid video encoding parameters. The prediction error is inserted into encoding data and encoded parameters determined to be accurately predicted with the addition of the prediction error are dropped. A new video stream is encoded with the predication error and without the dropped encoding parameters.

Patent Agency Ranking