专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11477462B2 Entropy coding using transform class 有权
公开(公告)号：US11477462B2
公开(公告)日：2022-10-18
申请号：US17121820
申请日：2020-12-15
申请人： GOOGLE LLC
发明人： Joseph Young , Dake He
IPC分类号： 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
摘要： 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.

2. 发明授权

US11178409B2 Probability mapping for entropy coding 有权
公开(公告)号：US11178409B2
公开(公告)日：2021-11-16
申请号：US16812539
申请日：2020-03-09
申请人： GOOGLE LLC
发明人： Joseph Young , Dake He
IPC分类号： H04N19/176 , H04N19/13 , H04N19/18 , H04N19/129 , H04N19/91 , H04N19/93 , H04N19/147 , H04N19/184 , H04N19/124 , H04N19/159 , H04N19/44 , H04N19/122
摘要： 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.

3. 发明授权

US11070843B2 Coding of last significant coefficient flags 有权
公开(公告)号：US11070843B2
公开(公告)日：2021-07-20
申请号：US17001715
申请日：2020-08-25
申请人： GOOGLE LLC
发明人： Dake He
IPC分类号： H04N19/61 , H04N19/174 , H04N19/64 , H04N19/91 , H04N19/70 , H04N19/18
摘要： 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.

4. 发明授权

US10999467B2 Context-adaptive scanning 有权
公开(公告)号：US10999467B2
公开(公告)日：2021-05-04
申请号：US16885383
申请日：2020-05-28
申请人： Google LLC
发明人： Oleg Golubitsky , Dake He
IPC分类号： H04N1/32 , H04N1/00
摘要： 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.

5. 发明申请

US20210120249A1 Using Multiple Models For Entropy Coding In Video Compression 有权
公开(公告)号：US20210120249A1
公开(公告)日：2021-04-22
申请号：US17136200
申请日：2020-12-29
申请人： GOOGLE LLC
发明人： Dake He
IPC分类号： H04N19/13 , H04N19/124 , H04N19/159 , H04N19/176 , H04N19/196 , H04N19/91 , H04N19/96 , H04N19/18
摘要： 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.

6. 发明授权

US10951894B2 Transform block-level scan order selection for video coding 有权
公开(公告)号：US10951894B2
公开(公告)日：2021-03-16
申请号：US16535154
申请日：2019-08-08
申请人： GOOGLE LLC
发明人： Jingning Han , Dake He
IPC分类号： H04N19/129 , H04N19/176 , H04N19/18 , H04N19/61 , H04N19/82
摘要： 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.

7. 发明申请

US20200280717A1 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
申请人： GOOGLE LLC
发明人： Shan Li , Claudionor Coelho , Aki Kuusela , Dake He
IPC分类号： H04N19/107 , H04N19/119 , H04N19/176 , H04N19/96 , G06N3/04 , G06N3/08
摘要： 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.

8. 发明申请

US20200092556A1 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
申请人： GOOGLE LLC
发明人： Claudionor Coelho , Dake He , Aki Kuusela , Shan Li
IPC分类号： H04N19/124 , H04N19/176 , H04N19/96 , H04N19/164
摘要： 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.

9. 发明申请

US20200092552A1 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
申请人： GOOGLE LLC
发明人： Claudionor Coelho , Aki Kuusela , Shan Li , Dake He
IPC分类号： H04N19/119 , H04N19/176 , H04N19/147 , H04N19/19
摘要： 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.

10. 发明申请

US20200053367A1 REFINED ENTROPY CODING FOR LEVEL MAPS 审中-公开
公开(公告)号：US20200053367A1
公开(公告)日：2020-02-13
申请号：US16659666
申请日：2019-10-22
申请人： GOOGLE LLC
发明人： Joseph Young , Dake He
IPC分类号： H04N19/18 , H04N19/44 , H04N19/159 , H04N19/124 , H04N19/129 , H04N19/13 , H04N19/176 , H04N19/184 , H04N19/147 , H04N19/93 , H04N19/91
摘要： An apparatus includes a memory and a processor. The processor is configured to execute instructions stored in the memory to obtain a transform type for decoding a transform block for the current block; select, based on the transform type, a template for coding a value of a non-zero map; select, based on the template, a context for entropy decoding the value of the non-zero map; and decode the value of the non-zero map based on the context. The non-zero map indicates which coefficients of the transform block have non-zero values. A method includes obtaining a transform class for coding a transform block for the current block, wherein the transform class corresponding to a transform type and a direction; selecting, based on the transform class, a coding context for coding a value of a non-zero map; and coding the value of the non-zero map based on the coding context.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式