公开(公告)号：US20230325959A1

公开(公告)日：2023-10-12

申请号：US17926213

申请日：2021-06-21

Applicant: Google LLC

Inventor： Dake He ,  Tianhao Zhang ,  Elnaz Barshan Tashnizi ,  Xiyang Luo ,  Huiwen Chang ,  Feng Yang ,  Ryan Matthew Haggarty

IPC: G06T1/00 ,  G06T3/40 ,  G06T5/20 ,  G06V10/764

CPC classification number: G06T1/0021 ,  G06T3/40 ,  G06T5/20 ,  G06V10/764 ,  G06T2201/0065 ,  G06T2207/20081

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting and decoding a visually imperceptible or perceptible watermark. A watermark detection apparatus determines whether the particular image includes a visually imperceptible or perceptible watermark using detector a machine learning model. If the watermark detection apparatus detects a watermark, the particular image is routed to a watermark decoder. If the watermark detection apparatus cannot detect a watermark in the particular image, the particular image is filtered from further processing. The watermark decoder decodes the visually imperceptible or perceptible watermark detected in the particular image. After decoding, an item depicted in the particular image is validated based data extracted from the decoded visually imperceptible or perceptible watermark.

公开(公告)号：US11477462B2

公开(公告)日：2022-10-18

申请号：US17121820

申请日：2020-12-15

Applicant: GOOGLE LLC

Inventor： Joseph Young ,  Dake He

IPC: H04N19/176 ,  H04N19/91 ,  H04N19/129 ,  H04N19/13 ,  H04N19/18 ,  H04N19/122 ,  H04N19/184 ,  H04N19/60 ,  H04N19/93 ,  H04N19/147 ,  H04N19/124 ,  H04N19/159 ,  H04N19/44

Abstract: An apparatus for decoding a current block includes a processor that is configured to obtain a transform class of a transform type used for decoding a transform block of the current block; select, based on the transform class, a template for coding a value related to a transform coefficient at a row and a column of the transform block; obtain, using the template, an index of a probability distribution in a table of probability distributions; and decode, from a compressed bitstream, the value using the probability distribution.

公开(公告)号：US11178409B2

公开(公告)日：2021-11-16

申请号：US16812539

申请日：2020-03-09

Applicant: GOOGLE LLC

Inventor： Joseph Young ,  Dake He

IPC: H04N19/176 ,  H04N19/13 ,  H04N19/18 ,  H04N19/129 ,  H04N19/91 ,  H04N19/93 ,  H04N19/147 ,  H04N19/184 ,  H04N19/124 ,  H04N19/159 ,  H04N19/44 ,  H04N19/122

Abstract: A method for coding a frame of a video stream includes selecting a first initial probability distribution for coding at least a first portion of the frame; updating, to obtain an updated first initial probability distribution and using backward adaptivity, the first initial probability distribution while coding the first portion of the frame; mapping the updated first initial probability distribution to a second initial probability distribution; and coding a second portion of the frame using the second initial probability distribution as an initial probability distribution. The first values of the first initial probability distribution are described using M bits, wherein M is a first positive integer. Second values of the updated first initial probability distribution are described using N bits, where N is a second positive integer that is greater than M. Third values of the second initial probability distribution are described using M bits.

公开(公告)号：US11070843B2

公开(公告)日：2021-07-20

申请号：US17001715

申请日：2020-08-25

Applicant: GOOGLE LLC

Inventor： Dake He

IPC: H04N19/61 ,  H04N19/174 ,  H04N19/64 ,  H04N19/91 ,  H04N19/70 ,  H04N19/18

Abstract: An apparatus for decoding a transform block that is decoded using a scan order includes a processor that is configured to decode, from an encoded bitstream, a first syntax element indicating a group of consecutive scan positions in the scan order, where the group of consecutive scan positions includes a scan position of a last non-zero coefficient; determine an offset within the group of consecutive scan positions of the last non-zero coefficient; and decode, from the encoded bitstream, coefficients up to the last non-zero coefficient of the transform block.

公开(公告)号：US10999467B2

公开(公告)日：2021-05-04

申请号：US16885383

申请日：2020-05-28

Applicant: Google LLC

Inventor： Oleg Golubitsky ,  Dake He

IPC: H04N1/32 ,  H04N1/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for context-adaptive scanning of digital components. In one aspect, a method comprises: selecting a given digital component from among a plurality of digital components based on a current scanning priority of the given digital component; scanning the given digital component, comprising determining a current state of the given digital component; determining a current context of the given digital component based on one or more of: (i) the current state of the given digital component, or (ii) a current scan index of the given digital component that specifies a number of times the given digital component has been scanned; determining an updated scanning priority of the given digital component based on the current context of the given digital component; and re-scanning the given digital component according to the updated scanning priority.

公开(公告)号：US20210120249A1

公开(公告)日：2021-04-22

申请号：US17136200

申请日：2020-12-29

Applicant: GOOGLE LLC

Inventor： Dake He

IPC: H04N19/13 ,  H04N19/124 ,  H04N19/159 ,  H04N19/176 ,  H04N19/196 ,  H04N19/91 ,  H04N19/96 ,  H04N19/18

Abstract: An apparatus for entropy coding a sequence of bits obtains, using a first probability distribution, a first conditional probability for coding a bit at a position within the sequence of bits, the first conditional probability being a conditional probability of the bit having a certain value given that a sub-sequence of the sequence of bits has first respective values; obtains, using a second probability distribution that is different from the first probability distribution, a second conditional probability for coding the bit, the second conditional probability being a conditional probability of the bit having the certain value given that the sub-sequence has second respective values; obtains, using the first conditional probability and the second conditional probability, a mixed probability for coding the bit; and codes the bit using the mixed probability.

公开(公告)号：US10951894B2

公开(公告)日：2021-03-16

申请号：US16535154

申请日：2019-08-08

Applicant: GOOGLE LLC

Inventor： Jingning Han ,  Dake He

IPC: H04N19/129 ,  H04N19/176 ,  H04N19/18 ,  H04N19/61 ,  H04N19/82

Abstract: A scan order for encoding or decoding coefficients of a transform block is selected on a transform block-level. A set of candidate scan orders is processed by identifying end of block positions within the transform block for each of the candidate scan orders. Cost values are determined for each of the candidate scan orders to reflect a number of the coefficients of the transform block that are located before the respective end of block positions. In particular, a cost value for a candidate scan order reflects the number of zero-value coefficients located before the end of block position for that candidate scan order. One of the candidate scan orders is then selected based on those cost values. The selected scan order is used to scan the coefficients in the transform block, such as for encoding those coefficients to a bitstream or for decoding those coefficients to an output video stream.

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.

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.

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.