公开(公告)号：US10609421B2

公开(公告)日：2020-03-31

申请号：US16033582

申请日：2018-07-12

Applicant: Google LLC

Inventor： Aki Kuusela ,  Dake He

IPC: H04N19/91 ,  H04N19/124 ,  H04N19/176 ,  H04N19/625

Abstract: Coding a transform block having transform coefficients is described. A plurality of register arrays is defined to each hold one or more stored values regarding the coding context based on at least one spatial template for a coding context. The register arrays are initialized by setting the stored values to default values, and values for the transform coefficients from the transform block are coded in a reverse scan order. The values for the transform coefficients are indicative of magnitudes of the transform coefficients. For each of one or more transform coefficients, the coding includes determining the coding context using at least some of the stored values from the register arrays, entropy coding a value for the transform coefficient using the coding context, and updating the register arrays subsequent to entropy coding the value for the transform coefficient.

公开(公告)号：US20190182507A1

公开(公告)日：2019-06-13

申请号：US15835501

申请日：2017-12-08

Applicant: GOOGLE LLC

Inventor： Aki Kuusela ,  Dake He

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

CPC classification number: H04N19/60 ,  H04N19/124 ,  H04N19/13 ,  H04N19/18 ,  H04N19/423

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.

公开(公告)号：US20190124349A1

公开(公告)日：2019-04-25

申请号：US15845161

申请日：2017-12-18

Applicant: GOOGLE LLC

Inventor： Aki Kuusela ,  Dake He

IPC: H04N19/513 ,  H04N19/70

Abstract: Motion estimation or compensation functionality of a hardware component is used to encode or decode key frames and other video frames. The hardware component includes a memory, which may, for example, be a local static random access memory or an external dynamic random access memory. Upon a block of a frame being encoded or decoded, data associated with that block is stored in the memory. That data can then be processed by motion estimation or motion compensation for use in encoding or decoding one or more later blocks within the same frame. The data may, for example, be stored in the memory after operations for reconstruction and loop filtering have been performed. The data stored in the memory may effectively be processed using traditional inter-prediction operations, such as to identify similar video objects within blocks of the same frame.

公开(公告)号：US12244803B2

公开(公告)日：2025-03-04

申请号：US18273666

申请日：2021-01-25

Applicant: Google LLC

Inventor： In Suk Chong ,  Hui Su ,  Aki Kuusela

IPC: H04N19/12 ,  H04N19/103 ,  H04N19/119 ,  H04N19/124 ,  H04N19/13 ,  H04N19/172 ,  H04N19/176 ,  H04N19/186 ,  H04N19/61

Abstract: For a coding block of an image, a luma prediction block is generated, a luma residual block is generated, a quantized luma block is generated after transforming the luma residual block using a luma transform type, and the quantized luma block is entropy encoded. A chroma prediction block is generated, a chroma residual block is generated, an initial chroma transform type for the chroma residual block is determined as the luma transform type, a quantized chroma block is generated using the chroma residual block transformed by a final chroma transform type, and the quantized chroma block is entropy encoded. When the initial chroma transform type is other than a default transform type, the final chroma transform type is the initial chroma transform type or the default transform type, and quantized coefficients of the quantized chroma block depend upon quantized coefficients of the quantized luma block.

公开(公告)号：US20240089433A1

公开(公告)日：2024-03-14

申请号：US18273666

申请日：2021-01-25

Applicant: Google LLC

Inventor： In Suk Chong ,  Hui Su ,  Aki Kuusela

IPC: H04N19/12 ,  H04N19/103 ,  H04N19/119 ,  H04N19/124 ,  H04N19/13 ,  H04N19/172 ,  H04N19/176 ,  H04N19/186 ,  H04N19/61

CPC classification number: H04N19/12 ,  H04N19/103 ,  H04N19/119 ,  H04N19/124 ,  H04N19/13 ,  H04N19/172 ,  H04N19/176 ,  H04N19/186 ,  H04N19/61

Abstract: For a coding block of an image, a luma prediction block is generated, a luma residual block is generated, a quantized luma block is generated after transforming the luma residual block using a luma transform type, and the quantized luma block is entropy encoded. A chroma prediction block is generated, a chroma residual block is generated, an initial chroma transform type for the chroma residual block is determined as the luma transform type, a quantized chroma block is generated using the chroma residual block transformed by a final chroma transform type, and the quantized chroma block is entropy encoded. When the initial chroma transform type is other than a default transform type, the final chroma transform type is the initial chroma transform type or the default transform type, and quantized coefficients of the quantized chroma block depend upon quantized coefficients of the quantized luma block.

公开(公告)号：US20230330533A1

公开(公告)日：2023-10-19

申请号：US18213399

申请日：2023-06-23

Applicant: GOOGLE LLC

Inventor： Clinton Smullen ,  Dov Zimring ,  Jani Huoponen ,  Aki Kuusela ,  Jean-Francois Roy ,  Paul Lalonde ,  Paul Leventis

IPC: A63F13/53 ,  A63F13/35 ,  A63F13/358

CPC classification number: A63F13/53 ,  A63F13/35 ,  A63F13/358 ,  A63F13/86

Abstract: This application is directed to a method of managing processing capability of a server system having one or more processing cores that further include multiple processing slices. Upon receiving requests to initiate online gaming sessions, the server system allocates each processing slice of the processing cores to a subset of the online gaming sessions to be executed thereon. A first processing slice is allocated to a first subset of the online gaming sessions including a first gaming session and a second gaming session. At the first processing slice, a time-sharing processing schedule is determined for the first subset of the online gaming sessions. In accordance with the time-sharing processing schedule, the first and second gaming sessions share a duty cycle of the first processing slice, and are executed dynamically and in parallel according to real-time data processing need of the first and second gaming sessions.

公开(公告)号：US20230229895A1

公开(公告)日：2023-07-20

申请号：US18007871

申请日：2021-06-02

Applicant: Google LLC

Inventor： Claudionor Jose Nunes Coelho, Jr. ,  Piotr Zielinski ,  Aki Kuusela ,  Shan Li ,  Hao Zhuang

IPC: G06N3/0495 ,  G06N3/092

CPC classification number: G06N3/0495 ,  G06N3/092

Abstract: Systems and methods for producing a neural network architecture with improved energy consumption and performance tradeoffs are disclosed, such as would be deployed for use on mobile or other resource-constrained devices. In particular, the present disclosure provides systems and methods for searching a network search space for joint optimization of a size of a layer of a reference neural network model (e.g., the number of filters in a convolutional layer or the number of output units in a dense layer) and of the quantization of values within the layer. By defining the search space to correspond to the architecture of a reference neural network model, examples of the disclosed network architecture search can optimize models of arbitrary complexity. The resulting neural network models are able to be run using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art, mobile-optimized models.

公开(公告)号：US11701587B2

公开(公告)日：2023-07-18

申请号：US17521133

申请日：2021-11-08

Applicant: GOOGLE LLC

Inventor： Clinton Smullen ,  Dov Zimring ,  Jani Huoponen ,  Aki Kuusela ,  Jean-Francois Roy ,  Paul Lalonde ,  Paul Leventis

IPC: A63F13/358 ,  A63F13/53 ,  A63F13/35 ,  A63F13/86

CPC classification number: A63F13/53 ,  A63F13/35 ,  A63F13/358 ,  A63F13/86

Abstract: This application is directed to a method of managing processing capability of a server system having one or more processing cores that further include multiple processing slices. Upon receiving requests to initiate online gaming sessions, the server system allocates each processing slice of the processing cores to a subset of the online gaming sessions to be executed thereon. A first processing slice is allocated to a first subset of the online gaming sessions including a first gaming session and a second gaming session. At the first processing slice, a time-sharing processing schedule is determined for the first subset of the online gaming sessions. In accordance with the time-sharing processing schedule, the first and second gaming sessions share a duty cycle of the first processing slice, and are executed dynamically and in parallel according to real-time data processing need of the first and second gaming sessions.

公开(公告)号：US20220201316A1

公开(公告)日：2022-06-23

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 ,  H04N19/176 ,  H04N19/96 ,  G06T9/00

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.

公开(公告)号：US11218737B2

公开(公告)日：2022-01-04

申请号：US16042261

申请日：2018-07-23

Applicant: GOOGLE LLC

Inventor： Jingning Han ,  Aki Kuusela ,  Stanislav Vitvitskyy ,  Yaowu Xu ,  Ching-Han Chiang ,  Dake He

IPC: H04N19/91 ,  H04N19/44 ,  H04N19/61 ,  H04N19/70

Abstract: Asymmetric probability model updating and entropy coding includes using different numbers of bits for storing probabilities of a probability model and for entropy coding symbols using that probability model. The probabilities of a probability model are updated according to values of syntax elements decoded from a bitstream. The probabilities are associated with possible values of the syntax elements and are stored using a first bit precision. Based on the updated probabilities, a second bit precision to use to entropy decode the syntax elements is determined. The second bit precision is less than the first bit precision. The syntax elements are then entropy decoded using the second bit precision, such as to produce quantized transform coefficients, which may be further processed and output to an output video stream. Using the first bit precision to entropy decode the syntax elements results in a lower compression throughput than using the second bit precision.