中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

99 records (took 0.024 seconds)

    GUIDED RESTORATION OF VIDEO DATA USING NEURAL NETWORKS
    51.
    发明申请
    GUIDED RESTORATION OF VIDEO DATA USING NEURAL NETWORKS 有权

    公开(公告)号：US20220207654A1

    公开(公告)日：2022-06-30

    申请号：US17698116

    申请日：2022-03-18

    Applicant: GOOGLE LLC

    Inventor： Debargha Mukherjee ,  Urvang Joshi ,  Yue Chen ,  Sarah Parker

    IPC: G06T5/00 ,  G06T5/50 ,  G06N3/08 ,  G06N3/04 ,  G06N20/20 ,  G06T3/40 ,  H04N19/70 ,  H04N19/176 ,  G06K9/62 ,  G06T9/00

    Abstract: Guided restoration is used to restore video data degraded from a video frame. The video frame is divided into restoration units (RUs) which each correspond to one or more blocks of the video frame. Restoration schemes are selected for each RU. The restoration schemes may indicate to use one of a plurality of neural networks trained for the guided restoration. Alternatively, the restoration schemes may indicate to use a neural network and a filter-based restoration tool. The video frame is then restored by processing each RU according to the respective selected restoration scheme. During encoding, the restored video frame is encoded to an output bitstream, and the use of the selected restoration schemes may be signaled within the output bitstream. During decoding, the restored video frame is output to an output video stream.

    Inter-prediction mode-dependent transforms for video coding
    52.
    发明授权
    Inter-prediction mode-dependent transforms for video coding 有权

    公开(公告)号：US11197004B1

    公开(公告)日：2021-12-07

    申请号：US16919507

    申请日：2020-07-02

    Applicant: Google LLC

    Inventor： Rohit Singh ,  Debargha Mukherjee ,  Elliott Karpilovsky ,  Lester Lu

    IPC: H04N19/184 ,  H04N19/124 ,  H04N19/61

    Abstract: Transform modes are derived for inter-predicted blocks using side information available within a bitstream. An inter-predicted encoded video block and side information are identified within a bitstream. Based on the side information, a trained transform is determined for inverse transforming transform coefficients of the inter-predicted encoded video block from amongst multiple trained transforms. The transform coefficients of the inter-predicted encoded video block are inverse transformed according to the trained transform to produce a prediction residual. A video block is reconstructed using the prediction residual and the reference frame. The video block is then output within an output video stream for storage or display. To determine the trained transforms, a learning model uses individual side information types and combinations of the individual side information types processed against a training data set.

    RESTORATION IN VIDEO CODING USING FILTERING AND SUBSPACE PROJECTION
    55.
    发明申请
    RESTORATION IN VIDEO CODING USING FILTERING AND SUBSPACE PROJECTION 审中-公开

    公开(公告)号：US20200068224A1

    公开(公告)日：2020-02-27

    申请号：US16666676

    申请日：2019-10-29

    Applicant: GOOGLE LLC

    Inventor： Debargha Mukherjee

    IPC: H04N19/86 ,  H04N19/176 ,  H04N19/136 ,  H04N19/117 ,  G06T5/00 ,  H04N19/192 ,  H04N19/85 ,  H04N19/174 ,  H04N19/80 ,  H04N19/46 ,  H04N19/182

    Abstract: A method includes generating, using first restoration parameters, a first guide tile for a degraded tile of the degraded frame, the degraded tile corresponding to a source tile of the source frame; generating, using second restoration parameters, a second guide tile for the degraded tile of the degraded frame, the second restoration parameters being different from the first restoration parameters; determining a first tile difference between the source tile and the first guide tile; determining a second tile difference between the source tile and the second guide tile; calculating projection parameters that minimize a difference between a restored tile of the degraded tile and the source tile; and encoding, in an encoded bitstream, the projection parameters. The difference between the restored tile of the degraded tile and the source tile is a linear combination, using the projection parameters, of the first tile difference and the second tile difference.

    SEGMENTATION-BASED PARAMETERIZED MOTION MODELS
    60.
    发明申请
    SEGMENTATION-BASED PARAMETERIZED MOTION MODELS 审中-公开

    公开(公告)号：US20180270497A1

    公开(公告)日：2018-09-20

    申请号：US15838748

    申请日：2017-12-12

    Applicant: GOOGLE LLC

    Inventor： Debargha Mukherjee ,  Yuxin Liu ,  Sarah Parker

    IPC: H04N19/517 ,  H04N19/513 ,  H04N19/80 ,  H04N19/557

    CPC classification number: H04N19/517 ,  H04N19/17 ,  H04N19/20 ,  H04N19/521 ,  H04N19/54 ,  H04N19/543 ,  H04N19/547 ,  H04N19/557 ,  H04N19/80

    Abstract: Encoding and decoding using parametrized motion models are disclosed. A method includes segmenting the video frame with respect to a reference frame resulting in a segmentation, determining a first motion vector for the current block based on the segmentation, determining a second motion vector for the current block using translational motion compensation, and encoding, for the current block, the one of the first motion vector and the second motion vector corresponding to a smaller error. The segmentation includes a segment containing the current block and a parameterized motion model for the segment. Another method includes identifying a parameterized motion model corresponding to a motion model type, associating the parameterized motion model with a segment of a reference frame, and, in response to determining that the current block is encoded using the parameterized motion model, decoding the current block using the parameterized motion model.

Patent Agency Ranking