知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

28 records (took 0.016 seconds)

    MULTI-SCALE OPTICAL FLOW FOR LEARNED VIDEO COMPRESSION
    2.
    发明申请
    MULTI-SCALE OPTICAL FLOW FOR LEARNED VIDEO COMPRESSION 有权

    公开(公告)号：US20220303568A1

    公开(公告)日：2022-09-22

    申请号：US17207244

    申请日：2021-03-19

    Applicant: QUALCOMM Incorporated

    Inventor： Reza POURREZA ,  Amir SAID ,  Yang YANG ,  Yinhao ZHU ,  Taco Sebastiaan COHEN

    IPC: H04N19/51 ,  H04N19/172 ,  H04N19/137 ,  H04N19/107 ,  H04N19/593 ,  G06N3/08

    Abstract: Systems and techniques are described for encoding and/or decoding data based on motion estimation that applies variable-scale warping. An encoding device can receive an input frame and a reference frame that depict a scene at different times. The encoding device can generate an optical flow identifying movements in the scene between the two frames. The encoding device can generate a weight map identifying how finely or coarsely the reference frame can be warped for input frame prediction. The encoding device can generate encoded video data based on the optical flow and the weight map. A decoding device can generate a reconstructed optical flow and a reconstructed weight map from the encoded data. A decoding device can generate a prediction frame by warping the reference frame based on the reconstructed optical flow and the reconstructed weight map. The decoding device can generate a reconstructed input frame based on the prediction frame.

    PROGRESSIVE DATA COMPRESSION USING ARTIFICIAL NEURAL NETWORKS
    4.
    发明申请
    PROGRESSIVE DATA COMPRESSION USING ARTIFICIAL NEURAL NETWORKS 有权

    公开(公告)号：US20220237740A1

    公开(公告)日：2022-07-28

    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: G06T3/40 ,  G06T9/00

    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.

    INSTANCE-ADAPTIVE IMAGE AND VIDEO COMPRESSION USING MACHINE LEARNING SYSTEMS
    5.
    发明公开
    INSTANCE-ADAPTIVE IMAGE AND VIDEO COMPRESSION USING MACHINE LEARNING SYSTEMS 审中-公开

    公开(公告)号：US20240205427A1

    公开(公告)日：2024-06-20

    申请号：US18420635

    申请日：2024-01-23

    Applicant: QUALCOMM Incorporated

    Inventor： Ties Jehan VAN ROZENDAAL ,  Iris Anne Marie HUIJBEN ,  Taco Sebastiaan COHEN

    IPC: H04N19/184 ,  G06N3/045 ,  G06N3/088

    CPC classification number: H04N19/184 ,  G06N3/045 ,  G06N3/088

    Abstract: Techniques are described for compressing data using machine learning systems and tuning machine learning systems for compressing the data. An example process can include receiving, by a neural network compression system (e.g., trained on a training dataset), input data for compression by the neural network compression system. The process can include determining a set of updates for the neural network compression system, the set of updates including updated model parameters tuned using the input data. The process can include generating, by the neural network compression system using a latent prior, a first bitstream including a compressed version of the input data. The process can further include generating, by the neural network compression system using the latent prior and a model prior, a second bitstream including a compressed version of the updated model parameters. The process can include outputting the first bitstream and the second bitstream for transmission to a receiver.

    LEARNED B-FRAME CODING USING P-FRAME CODING SYSTEM
    6.
    发明公开
    LEARNED B-FRAME CODING USING P-FRAME CODING SYSTEM 审中-公开

    公开(公告)号：US20240022761A1

    公开(公告)日：2024-01-18

    申请号：US18343618

    申请日：2023-06-28

    Applicant: QUALCOMM Incorporated

    Inventor： Reza POURREZA ,  Taco Sebastiaan COHEN

    IPC: H04N19/59 ,  G06N3/063 ,  G06N3/088 ,  G06N3/045

    CPC classification number: H04N19/59 ,  G06N3/063 ,  G06N3/088 ,  G06N3/045

    Abstract: Techniques are described for processing video data, such as by performing learned bidirectional coding using a unidirectional coding system and an interpolated reference frame. For example, a process can include obtaining a first reference frame and a second reference frame. The process can include generating a third reference frame at least in part by performing interpolation between the first reference frame and the second reference frame. The process can include performing unidirectional inter-prediction on an input frame based on the third reference frame, such as by estimating motion between an input frame and the third reference frame, and generating a warped frame at least in part by warping one or more pixels of the third reference frame based on the estimated motion. The process can include generating, based on the warped frame and a predicted residual, a reconstructed frame representing the input frame, the reconstructed frame including a bidirectionally-predicted frame.

    TRANSFORMER-BASED ARCHITECTURE FOR TRANSFORM CODING OF MEDIA
    10.
    发明申请
    TRANSFORMER-BASED ARCHITECTURE FOR TRANSFORM CODING OF MEDIA 有权

    公开(公告)号：US20230100413A1

    公开(公告)日：2023-03-30

    申请号：US17486732

    申请日：2021-09-27

    Applicant: QUALCOMM Incorporated

    Inventor： Yinhao ZHU ,  Yang YANG ,  Taco Sebastiaan COHEN

    IPC: H04N19/60

    Abstract: Systems and techniques are described herein for processing media data using a neural network system. For instance, a process can include obtaining a latent representation of a frame of encoded image data and generating, by a plurality of decoder transformer layers of a decoder sub-network using the latent representation of the frame of encoded image data as input, a frame of decoded image data. At least one decoder transformer layer of the plurality of decoder transformer layers includes: one or more transformer blocks for generating one or more patches of features and determine self-attention locally within one or more window partitions and shifted window partitions applied over the one or more patches; and a patch un-merging engine for decreasing a respective size of each patch of the one or more patches.

Patent Agency Ranking