公开(公告)号：US20230141888A1

公开(公告)日：2023-05-11

申请号：US17917540

申请日：2020-04-08

申请人： Google LLC

发明人： Jyrki Alakuijala ,  Luca Versari

IPC分类号： H04N19/119 ,  H04N19/154 ,  H04N19/86 ,  H04N19/176

CPC分类号： H04N19/119 ,  H04N19/154 ,  H04N19/86 ,  H04N19/176

摘要： A method for partitioning a block of an image to reduce quantization artifacts includes estimating an expected entropy of the block; partitioning the block into sub-blocks, where each sub-block having a size of a smallest possible partition size; calculating respective amounts of visual masking for the sub-blocks; selecting, as a visual masking characteristic of the block, a highest visual masking value of the respective amounts of visual masking for the sub-blocks; combining the visual masking characteristic of the block and the expected entropy of the block to obtain a splitting indicator value; and determining whether to split the block based on the splitting indicator.
The changes to the abstract are shown below:
A method for partitioning a block of an image to reduce quantization artifacts includes estimating an expected entropy of the block; partitioning the block into sub-blocks, where each sub-block having a size of a smallest possible partition size; calculating respective amounts of visual masking for the sub-blocks; selecting, as a visual masking characteristic of the block, a highest visual masking value of the respective amounts of visual masking for the sub-blocks; combining the visual masking characteristic of the block and the expected entropy of the block to obtain a splitting indicator value; and determining whether to split the block based on the splitting indicator.

公开(公告)号：US11457239B2

公开(公告)日：2022-09-27

申请号：US15807622

申请日：2017-11-09

申请人： GOOGLE LLC

发明人： Jyrki Alakuijala ,  Zoltan Szabadka

IPC分类号： H04N11/02 ,  H04N19/597 ,  H04N19/44 ,  H04N19/176 ,  H04N19/13 ,  H04N19/124 ,  H04N19/61 ,  H04N19/82 ,  H04N19/18 ,  H04N19/117 ,  H04N19/14 ,  H04N19/167 ,  H04N19/60 ,  H04N19/86

摘要： Video decoding may include transform coefficient continuity smoothing, which may include coefficient continuity smoothing, defined correlation coefficient smoothing, pixel range projection, and luminance correlated chrominance resampling. Coefficient continuity smoothing may include obtaining encoded block data from the encoded bitstream, the encoded block data corresponding to a current block from the reconstructed frame, and generating reconstructed block data for the current block based on the encoded block data using transform coefficient continuity smoothing. Transform coefficient continuity smoothing may include, for a block boundary of the current block, in response to a determination that adjacent block data corresponding to an adjacent block spatially adjacent to the current block along the block boundary is available, performing transform coefficient continuity smoothing based on the current block, the adjacent block, and the block boundary, and including the reconstructed block data in the reconstructed frame, and outputting the reconstructed frame.

公开(公告)号：US11166022B2

公开(公告)日：2021-11-02

申请号：US16430889

申请日：2019-06-04

申请人： GOOGLE LLC

发明人： Jyrki Alakuijala ,  George Toderici

IPC分类号： H04N19/124 ,  H04N19/117 ,  H04N19/82

摘要： Artificial image generation may include obtaining a source image, identifying quantization information from the source image, wherein identifying the quantization information includes identifying multiresolution quantization interval information from the source image, generating a restoration filtered image by restoration filtering the source image, generating a constrained restoration filtered image by constraining the restoration filtered image based on the quantization information, obtaining an unconstrained artificial image based on the constrained restoration filtered image and a generative artificial neural network obtained using a generative adversarial network, obtaining the artificial image by constraining the unconstrained artificial image based on the quantization information, and outputting the artificial image.

公开(公告)号：US20200329240A1

公开(公告)日：2020-10-15

申请号：US16858802

申请日：2020-04-27

申请人： GOOGLE LLC

发明人： Jyrki Alakuijala ,  Lode Vandevenne ,  Thomas Fischbacher

IPC分类号： H04N19/117 ,  H04N19/137 ,  H04N19/176 ,  H04N19/182 ,  H04N19/86

摘要： An image block is coded using entropy-inspired directional filtering. During encoding, intensity differences are determined for at least some pixels of an image block based on neighboring pixels of respective ones of the at least some pixels. Angles are estimated for each of those pixels based on the intensity differences. A main filtering direction of the image block is then determined based on the estimated angles. The image block is filtered according to the main filtering direction to remove artifacts along oblique edges associated with the image block. The filtered image block is then encoded to an encoded image. During decoding, an angular map indicating angles estimated for pixels of an encoded image block is received and used to determine the main filtering direction of the image block. The image block can then be filtered according to the main filtering direction and then output for display or storage.

公开(公告)号：US20190356916A1

公开(公告)日：2019-11-21

申请号：US15985317

申请日：2018-05-21

申请人： Google LLC

发明人： Krzysztof Potempa ,  Jyrki Alakuijala ,  Robert Obryk

IPC分类号： H04N19/122 ,  H04N19/176 ,  H04N19/625

摘要： An image encoder includes a processor and a memory. The memory includes instructions configured to cause the processor to perform operations. In one example implementation, the operations may include determining whether a dictionary item is available for replacing a block of an image being encoded, the determining based on a hierarchical lookup mechanism, and encoding the image along with reference information of the dictionary item in response to determining that the dictionary item is available. In one more example implementation, the operations may include performing principal component analysis (PCA) on a block to generate a corresponding projected block, the block being associated with a group of images, comparing the projected block with a corresponding threshold, descending the block recursively based on the threshold until a condition is satisfied, and identifying a left over block as a cluster upon satisfying of the condition.

公开(公告)号：US20240276018A1

公开(公告)日：2024-08-15

申请号：US18643085

申请日：2024-04-23

申请人： GOOGLE LLC

发明人： Jyrki Alakuijala ,  Robert Obryk ,  Evgenii Kliuchnikov ,  Zoltan Szabadka ,  Jan Wassenberg ,  Minttu Alakuijala ,  Lode Vandevenne

IPC分类号： H04N19/65 ,  H04N19/124 ,  H04N19/18 ,  H04N19/184 ,  H04N19/85

CPC分类号： H04N19/65 ,  H04N19/124 ,  H04N19/18 ,  H04N19/184 ,  H04N19/85

摘要： The loss of image quality during compression is controlled using a sequence of quality control metrics. The sequence of quality control metrics is selected for quantizing transform coefficients within an area of the image based on an error level definition. Candidate bit costs are then determined by quantizing the transform coefficients according to the error level definition or a modified error level and the sequence of quality control metrics. Where the candidate bit cost resulting from using the modified error level is lower than the candidate bit cost resulting from using the error level definition, the transform coefficients are quantized according to the modified error level and the sequence of quality control metrics. Otherwise, the transform coefficients are quantized based on the error level definition and according to the sequence of quality control metrics.

公开(公告)号：US11734568B2

公开(公告)日：2023-08-22

申请号：US16274599

申请日：2019-02-13

申请人： Google LLC

发明人： Jyrki Alakuijala ,  Ruud van Asseldonk ,  Robert Obryk ,  Krzysztof Potempa

IPC分类号： G06N3/082 ,  G06N3/084 ,  G06N20/20 ,  G06N3/045

CPC分类号： G06N3/082 ,  G06N3/045 ,  G06N3/084 ,  G06N20/20

摘要： The present disclosure provides systems and methods for modification (e.g., pruning, compression, quantization, etc.) of artificial neural networks based on estimations of the utility of network connections (also known as “edges”). In particular, the present disclosure provides novel techniques for estimating the utility of one or more edges of a neural network in a fashion that requires far less expenditure of resources than calculation of the actual utility. Based on these estimated edge utilities, a computing system can make intelligent decisions regarding network pruning, network quantization, or other modifications to a neural network. In particular, these modifications can reduce resource requirements associated with the neural network. By making these decisions with knowledge of and based on the utility of various edges, this reduction in resource requirements can be achieved with only a minimal, if any, degradation of network performance (e.g., prediction accuracy).

公开(公告)号：US11695919B2

公开(公告)日：2023-07-04

申请号：US17093926

申请日：2020-11-10

申请人： GOOGLE LLC

发明人： Jyrki Alakuijala ,  Alexander Rhatushnyak

IPC分类号： H04N19/105 ,  H04N19/91 ,  H04N19/176 ,  H04N19/186 ,  H04N19/96

CPC分类号： H04N19/105 ,  H04N19/176 ,  H04N19/186 ,  H04N19/91 ,  H04N19/96

摘要： An apparatus includes a processor that is configured to select a palette entry in the palette for coding a value of a pixel of the image block; obtain respective palette indexes of neighboring pixels of the pixel; select, using the respective palette indexes, an entropy code for coding an index of the palette entry; and code the palette entry using the entropy code. A method includes obtaining respective palette indexes of neighboring pixels of a pixel of the image block; selecting an entropy code using the respective palette indexes; decoding, from a encoded bitstream, an index of a palette entry; and setting a value of the pixel using the palette entry.

公开(公告)号：US11212527B2

公开(公告)日：2021-12-28

申请号：US16858802

申请日：2020-04-27

申请人： GOOGLE LLC

发明人： Jyrki Alakuijala ,  Lode Vandevenne ,  Thomas Fischbacher

IPC分类号： H04N19/137 ,  H04N19/176 ,  H04N19/182 ,  H04N19/117 ,  H04N19/86

摘要： An image block is coded using entropy-inspired directional filtering. During encoding, intensity differences are determined for at least some pixels of an image block based on neighboring pixels of respective ones of the at least some pixels. Angles are estimated for each of those pixels based on the intensity differences. A main filtering direction of the image block is then determined based on the estimated angles. The image block is filtered according to the main filtering direction to remove artifacts along oblique edges associated with the image block. The filtered image block is then encoded to an encoded image. During decoding, an angular map indicating angles estimated for pixels of an encoded image block is received and used to determine the main filtering direction of the image block. The image block can then be filtered according to the main filtering direction and then output for display or storage.

公开(公告)号：US20200092558A1

公开(公告)日：2020-03-19

申请号：US16687719

申请日：2019-11-19

申请人： GOOGLE LLC

发明人： Jyrki Alakuijala ,  Jan Wassenberg

IPC分类号： H04N19/124 ,  H04N19/80 ,  H04N19/70 ,  H04N19/44 ,  H04N19/172

摘要： A spatially adaptive quantization-aware deblocking filter is used for encoding or decoding video or image frames. The deblocking filter receives a reconstructed frame produced based on dequantized and inverse transformed coefficients of a video frame or an image frame. The reconstructed frame is filtered according to adaptive quantization field data for the video or image frame. The adaptive quantization field data represents weights applied to quantization values used at different areas of the video or image frame. A number of blocking artifacts remaining within the resulting filtered frame is determined. The adaptive quantization field data is then adjusted based on that number of blocking artifacts. The filtered frame is then filtered according to the adjusted adaptive quantization field data. The resulting re-filtered frame is then output to an output source, such as for transmission, display, storage, or further processing.