中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

34 records (took 0.053 seconds)

    Ultra Light Models and Decision Fusion for Fast Video Coding
    1.
    发明申请
    Ultra Light Models and Decision Fusion for Fast Video Coding 有权

    公开(公告)号：US20230007284A1

    公开(公告)日：2023-01-05

    申请号：US17779380

    申请日：2019-12-23

    Applicant: Google LLC

    Inventor： Shan Li ,  Claudionor Coelho ,  In Suk Chong ,  Aki Kuusela

    IPC: H04N19/436 ,  H04N19/176 ,  H04N19/593 ,  H04N19/159 ,  H04N19/11 ,  H04N19/124 ,  H04N19/149

    Abstract: Ultra light models and decision fusion for increasing the speed of intra-prediction are described. Using a machine-learning (ML) model, an ML intra-prediction mode is obtained. A most-probable intra-prediction mode is obtained from amongst available intra-prediction modes for encoding the current block. As an encoding intra-prediction mode, one of the ML intra-prediction mode or the most-probable intra-prediction mode is selected, and the encoding intra-prediction mode is encoded in a compressed bitstream. A current block is encoded using the encoding intra-prediction mode. Selection of the encoding intra-prediction mode is based on relative reliabilities of the ML intra-prediction mode and the most-probable intra-prediction mode.

    RECEPTIVE-FIELD-CONFORMING CONVOLUTION MODELS FOR VIDEO CODING
    2.
    发明申请
    RECEPTIVE-FIELD-CONFORMING CONVOLUTION MODELS FOR VIDEO CODING 审中-公开

    公开(公告)号：US20200280717A1

    公开(公告)日：2020-09-03

    申请号：US16289149

    申请日：2019-02-28

    Applicant: GOOGLE LLC

    Inventor： Shan Li ,  Claudionor Coelho ,  Aki Kuusela ,  Dake He

    IPC: H04N19/107 ,  H04N19/119 ,  H04N19/176 ,  H04N19/96 ,  G06N3/04 ,  G06N3/08

    Abstract: Convolutional neural networks (CNN) that determine a mode decision (e.g., block partitioning) for encoding a block include feature extraction layers and multiple classifiers. A non-overlapping convolution operation is performed at a feature extraction layer by setting a stride value equal to a kernel size. The block has a N×N size, and a smallest partition output for the block has a S×S size. Classification layers of each classifier receive feature maps having a feature dimension. An initial classification layer receives the feature maps as an output of a final feature extraction layer. Each classifier infers partition decisions for sub-blocks of size (αS)×(αS) of the block, wherein α is a power of 2 and α=2, . . . , N/S, by applying, at some successive classification layers, a 1×1 kernel to reduce respective feature dimensions; and outputting by a last layer of the classification layers an output corresponding to a N/(αS)×N/(αS)×1 output map.

    Efficient Use of Quantization Parameters in Machine-Learning Models for Video Coding
    3.
    发明申请
    Efficient Use of Quantization Parameters in Machine-Learning Models for Video Coding 审中-公开

    公开(公告)号：US20200092556A1

    公开(公告)日：2020-03-19

    申请号：US16134134

    申请日：2018-09-18

    Applicant: GOOGLE LLC

    Inventor： Claudionor Coelho ,  Dake He ,  Aki Kuusela ,  Shan Li

    IPC: H04N19/124 ,  H04N19/176 ,  H04N19/96 ,  H04N19/164

    Abstract: A method for encoding an image block includes presenting, to a machine-learning model, the image block and a first value corresponding to a first quantization parameter; obtaining first mode decision parameters from the machine-learning model; and encoding the image block using the first mode decision parameters. The first value results from a non-linear function using the first quantization parameter as input. The machine-learning model is trained to output mode decision parameters by using training data. Each training datum includes a training block that is encoded by a second encoder, second mode decision parameters used by the second encoder for encoding the training block, and a second value corresponding to a second quantization parameter. The second encoder used the second quantization parameter for encoding the training block and the second value results from the non-linear function using the second quantization parameter as input.

    Receptive-Field-Conforming Convolutional Models for Video Coding
    4.
    发明申请
    Receptive-Field-Conforming Convolutional Models for Video Coding 审中-公开

    公开(公告)号：US20200092552A1

    公开(公告)日：2020-03-19

    申请号：US16134165

    申请日：2018-09-18

    Applicant: GOOGLE LLC

    Inventor： Claudionor Coelho ,  Aki Kuusela ,  Shan Li ,  Dake He

    IPC: H04N19/119 ,  H04N19/176 ,  H04N19/147 ,  H04N19/19

    Abstract: A convolutional neural network (CNN) for determining a partitioning of a block is disclosed. The block is of size N×N and a smallest partition is of size S×S. The CNN includes feature extraction layers; a concatenation layer that receives, from the feature extraction layers, first feature maps of the block, where each first feature map is of size S×S; and classifiers. Each classifier includes classification layers, each classification layer receives second feature maps having a respective feature dimension. Each classifier is configured to infer partition decisions for sub-blocks of size (αS)×(αS) of the block, wherein α is a power of 2 and α=2, . . . , N/S, by: applying, at some of successive classification layers of the classification layers, a kernel of size 1×1 to reduce the respective feature dimension in half; and outputting by a last layer of the classification layers an output corresponding to a N/(αS)×N/(αS)×1 output map.

    Using rate distortion cost as a loss function for deep learning
    7.
    发明授权
    Using rate distortion cost as a loss function for deep learning 有权

    公开(公告)号：US11956447B2

    公开(公告)日：2024-04-09

    申请号：US17601639

    申请日：2019-03-21

    Applicant: Google LLC

    Inventor： Claudionor Coelho ,  Aki Kuusela ,  Joseph Young ,  Shan Li ,  Dake He

    IPC: H04N19/147 ,  G06T9/00 ,  H04N19/176 ,  H04N19/96

    CPC classification number: H04N19/147 ,  G06T9/002 ,  H04N19/176 ,  H04N19/96

    Abstract: An apparatus for encoding an image block includes a processor that presents, to a machine-learning model, the image block, obtains the partition decision for encoding the image block from the model, and encodes the image block using the partition decision. The model is trained to output a partition decision for encoding the image block by using training data for a plurality of training blocks as input, the training data including for a training block, partition decisions for encoding the training block, and, for each partition decision, a rate-distortion value resulting from encoding the training block using the partition decision. The model is trained using a loss function combining a partition loss function based upon a relationship between the partition decisions and respective predicted partitions, and a rate-distortion cost loss function based upon a relationship between the rate-distortion values and respective predicted rate-distortion values.

    Receptive-field-conforming convolutional models for video coding
    8.
    发明授权
    Receptive-field-conforming convolutional models for video coding 有权

    公开(公告)号：US11310498B2

    公开(公告)日：2022-04-19

    申请号：US17086591

    申请日：2020-11-02

    Applicant: GOOGLE LLC

    Inventor： Claudionor Coelho ,  Aki Kuusela ,  Shan Li ,  Dake He

    IPC: H04N19/119 ,  H04N19/19 ,  H04N19/147 ,  H04N19/176

    Abstract: An apparatus for encoding a block of a picture includes a convolutional neural network (CNN) for determining a block partitioning of the block, the block having an N×N size and a smallest partition determined by the CNN being of size S×S. The CNN includes feature extraction layers; a concatenation layer that receives, from the feature extraction layers, first feature maps of the block, where each first feature map of the first feature maps is of the smallest possible partition size S×S of the block; and at least one classifier that is configured to infer partition decisions for sub-blocks of size (αS)×(αS) of the block, where α is a power of 2.

    RECEPTIVE-FIELD-CONFORMING CONVOLUTIONAL MODELS FOR VIDEO CODING
    9.
    发明申请
    RECEPTIVE-FIELD-CONFORMING CONVOLUTIONAL MODELS FOR VIDEO CODING 有权

    公开(公告)号：US20210051322A1

    公开(公告)日：2021-02-18

    申请号：US17086591

    申请日：2020-11-02

    Applicant: GOOGLE LLC

    Inventor： Claudionor Coelho ,  Aki Kuusela ,  Shan Li ,  Dake He

    IPC: H04N19/119 ,  H04N19/19 ,  H04N19/147 ,  H04N19/176

    Abstract: An apparatus for encoding a block of a picture includes a convolutional neural network (CNN) for determining a block partitioning of the block, the block having an N×N size and a smallest partition determined by the CNN being of size S×S. The CNN includes feature extraction layers; a concatenation layer that receives, from the feature extraction layers, first feature maps of the block, where each first feature map of the first feature maps is of the smallest possible partition size S×S of the block; and at least one classifier that is configured to infer partition decisions for sub-blocks of size (αS)×(αS) of the block, where α is a power of 2.

    Template-based entropy coding of quantized transform coefficients
    10.
    发明授权
    Template-based entropy coding of quantized transform coefficients 有权

    公开(公告)号：US10547869B2

    公开(公告)日：2020-01-28

    申请号：US15835501

    申请日：2017-12-08

    Applicant: GOOGLE LLC

    Inventor： Aki Kuusela ,  Dake He

    IPC: H04N19/60 ,  H04N19/18 ,  H04N19/13 ,  H04N19/124

    Abstract: A method of coding a transform block having transform coefficients includes selecting, based on a transform type used for the transform block, a spatial template for a coding context; defining shift registers to each hold one or more stored values regarding the coding context; initializing the shift registers by setting the stored values to default values; and coding values indicative of magnitudes of the transform coefficients from the transform block in a reverse scan order. Coding includes, for each of one or more values, obtaining a value to be coded at a scan position, determining the coding context using the stored values from the shift registers, entropy coding the value to be coded using the coding context, and subsequent to entropy coding the value to be coded, updating at least some of the stored values in the shift registers.

Patent Agency Ranking