知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

93 records (took 0.027 seconds)

    Progressive data compression using artificial neural networks
    1.
    发明授权
    Progressive data compression using artificial neural networks 有权

    公开(公告)号：US12008731B2

    公开(公告)日：2024-06-11

    申请号：US17648808

    申请日：2022-01-24

    Applicant: QUALCOMM Incorporated

    Inventor： Yadong Lu ,  Yang Yang ,  Yinhao Zhu ,  Amir Said ,  Taco Sebastiaan Cohen

    IPC: G06T3/4046 ,  G06T9/00

    CPC classification number: G06T3/4046 ,  G06T9/002

    Abstract: Certain aspects of the present disclosure provide techniques for compressing content using a neural network. An example method generally includes receiving content for compression. The content is encoded into a first latent code space through an encoder implemented by an artificial neural network trained to generate a latent space representation of the content. A first compressed version of the encoded content is generated using a first quantization bin size of a series of quantization bin sizes. A refined compressed version of the encoded content is generated by scaling the first compressed version of the encoded content into one or more second quantization bin sizes smaller than the first quantization bin size, conditioned at least on a value of the first compressed version of the encoded content. The refined compressed version of the encoded content is output for transmission.

    NEURAL-NETWORK MEDIA COMPRESSION USING QUANTIZED ENTROPY CODING DISTRIBUTION PARAMETERS
    2.
    发明公开
    NEURAL-NETWORK MEDIA COMPRESSION USING QUANTIZED ENTROPY CODING DISTRIBUTION PARAMETERS 审中-公开

    公开(公告)号：US20230262222A1

    公开(公告)日：2023-08-17

    申请号：US17814426

    申请日：2022-07-22

    Applicant: QUALCOMM Incorporated

    Inventor： Amir Said

    IPC: H04N19/13 ,  H04N19/124 ,  H04N19/42

    CPC classification number: H04N19/13 ,  H04N19/124 ,  H04N19/42

    Abstract: This disclosure describes entropy coding techniques for media data coded using neural-based techniques. A media coder is configured to determine a probability distribution function parameter for a data element of a data stream coded by a neural-based media compression technique, wherein the probability distribution function parameter is a function of a standard deviation of a probability distribution function of the data stream, determine a code vector based on the probability distribution function parameter, and entropy code the data element using the code vector.

    Joint termination of bidirectional data blocks for parallel coding
    3.
    发明授权
    Joint termination of bidirectional data blocks for parallel coding 有权

    公开(公告)号：US11677987B2

    公开(公告)日：2023-06-13

    申请号：US17224812

    申请日：2021-04-07

    Applicant: QUALCOMM Incorporated

    Inventor： Amir Said

    IPC: H04N19/91 ,  H04N19/44 ,  H04N19/436 ,  G06V10/82

    CPC classification number: H04N19/91 ,  G06V10/82 ,  H04N19/436 ,  H04N19/44

    Abstract: Techniques are described herein for processing video data. For instance, a process can include obtaining encoded video data. The process can include determining an intersection of values between values for a first termination byte of a first parcel of the encoded video data and values of a second termination byte of a second parcel of the encoded video data. The process can further include determining a joint termination byte for the first termination byte of the first parcel and the second termination byte of the second parcel. Values for the joint termination byte are based on the intersection of values. The process can include generating entropy coded data including the joint termination byte for the first parcel and the second parcel. The entropy coded data can be generated using arithmetic coding or binary coding.

    Implicit transform selection in video coding
    4.
    发明授权
    Implicit transform selection in video coding 有权

    公开(公告)号：US11539952B2

    公开(公告)日：2022-12-27

    申请号：US16815920

    申请日：2020-03-11

    Applicant: QUALCOMM Incorporated

    Inventor： Hilmi Enes Egilmez ,  Amir Said ,  Vadim Seregin ,  Marta Karczewicz

    IPC: H04N19/122 ,  H04N19/593 ,  H04N19/176 ,  H04N19/61

    Abstract: An example method includes inferring, for a current transform block of a current video block, a transform type from a plurality of transform types that includes one or more discrete cosine transforms (DCTs) and one or more discrete sine transforms (DSTs), wherein inferring the transform type comprises: determining a size of the current transform block; determining whether the current video block is partitioned using intra-subblock partitioning (ISP); and responsive to determining that the size of the current transform block is less than a threshold and that the current video block is partitioned using ISP, selecting a particular DST of the one or more DSTs as the selected transform type; transforming, using the selected transform type, the current transform block to obtain a block of reconstructed residual data for the video block; and reconstructing, based on the reconstructed residual data for the video block, the video block.

    Learned low-complexity adaptive quantization for video compression
    5.
    发明授权
    Learned low-complexity adaptive quantization for video compression 有权

    公开(公告)号：US11490083B2

    公开(公告)日：2022-11-01

    申请号：US17166639

    申请日：2021-02-03

    Applicant: QUALCOMM Incorporated

    Inventor： Amir Said ,  Reza Pourreza

    IPC: H04N19/124 ,  H04N19/176 ,  G06N20/00 ,  H04N19/186 ,  H04N19/18

    Abstract: A video encoder may determine a set of quantization offset parameters for a group of scaled transform coefficients for a block of video data based on side information associated with the block of video data. The video encoder may further quantize the group of scaled transform coefficients for the block of video data to generate quantized transform coefficients for the block of video data based at least in part on the set of quantization offset parameters. The video encoder may further generate an encoded video bitstream based at least in part on the quantized transform coefficients for the block of video data.

    Position-dependent prediction combinations in video coding
    7.
    发明授权
    Position-dependent prediction combinations in video coding 有权

    公开(公告)号：US10965941B2

    公开(公告)日：2021-03-30

    申请号：US16154261

    申请日：2018-10-08

    Applicant: QUALCOMM Incorporated

    Inventor： Xin Zhao ,  Vadim Seregin ,  Amir Said ,  Marta Karczewicz ,  Kai Zhang ,  Vijayaraghavan Thirumalai

    IPC: H04N7/12 ,  H04N19/11 ,  H04N19/117 ,  H04N19/176 ,  H04N19/105 ,  H04N19/593 ,  H04N19/167 ,  H04N19/182

    Abstract: A video coder may generate a predictor block using an intra prediction mode. As part of generating the predictor block, the video coder may, for each respective sample in a set of samples in the predictor block, determine, based on an initial value of the first weight and a distance between the respective sample and a first boundary of the predictor block, a value of the first weight for the respective sample. Additionally, the video coder may determine, based on the initial value of the second weight and a distance between the respective sample and a second boundary of the predictor block, a value of the second weight for the respective sample. The video coder may also determine a primary value for the respective sample. The video coder may then determine a secondary value for the respective sample based on the first weight, second weight, and the primary value.

Patent Agency Ranking