公开(公告)号：US11343528B2

公开(公告)日：2022-05-24

申请号：US17073892

申请日：2020-10-19

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  James Bankoski ,  Yue Chen ,  Yuxin Liu ,  Sarah Parker

IPC: H04N11/02 ,  H04N19/517 ,  H04N19/46 ,  H04N19/136 ,  H04N19/105 ,  H04N19/139 ,  H04N19/176 ,  H04N19/182

Abstract: Generating a compound predictor block of a current block of video can include generating, for the current block, predictor blocks comprising a first predictor block including first predictor pixels and a second predictor block including second predictor pixels; using at least a subset of the first predictor pixels to determine a first weight for a first predictor pixel of the first predictor pixels; obtaining a second weight for a second predictor pixel of the second predictor pixels, where the second predictor pixel is co-located with the first predictor pixel; and generating the compound predictor block by combining the first predictor block and the second predictor block, where the predictor block includes a weighted pixel that is determined using a weighted sum of the first predictor pixel and the second predictor pixel using the first weight and the second weight, respectively.

公开(公告)号：US20180160117A1

公开(公告)日：2018-06-07

申请号：US15789400

申请日：2017-10-20

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Yue Chen ,  Sarah Parker

IPC: H04N19/117 ,  H04N19/895 ,  H04N19/86 ,  H04N19/154 ,  H04N19/176

Abstract: Restoring a degraded tile of a degraded frame resulting from reconstruction is disclosed. A method includes, for a scaling factor of at least some scaling factors, recursively filtering the degraded tile using the scaling factor to generate a respective restored tile, and determining a respective error for the respective restored tile with respect to the source tile. The method also includes selecting an optimal scaling factor from the at least some scaling factors and encoding, in an encoded bitstream, a scaling parameter based on the optimal scaling factor. The optimal scaling factor corresponding to a smallest respective error. An apparatus includes a processor and non-transitory memory storing instructions. The instructions cause the processor to determine, from an encoded bitstream, a scaling factor, which determines how strongly edges in the degraded tile affect filtering operations, and recursively filter, resulting in a restored tile, the degraded tile using the scaling factor.

公开(公告)号：US20240333961A1

公开(公告)日：2024-10-03

申请号：US18742180

申请日：2024-06-13

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  James Bankoski ,  Yue Chen ,  Yuxin Liu ,  Sarah Parker

IPC: H04N19/517 ,  H04N19/105 ,  H04N19/136 ,  H04N19/139 ,  H04N19/176 ,  H04N19/182 ,  H04N19/46

CPC classification number: H04N19/517 ,  H04N19/105 ,  H04N19/136 ,  H04N19/139 ,  H04N19/176 ,  H04N19/182 ,  H04N19/46

Abstract: Generating a compound predictor block includes generating a first predictor block and generating a second predictor block. The first predictor block includes a first pixel and the second predictor block includes a second pixel. The first and the second pixels are located at a same location within the first predictor block and the second predictor block, respectively. A first weight is determined for the first pixel based on a difference between a first value of the first pixel and a second value of the second pixel. A second weight is determined for the second pixel based on the first weight. The compound predictor block is generated by combining the first predictor block and the second predictor block. The compound predictor block includes a weighted pixel that is determined based on a weighted sum of the first pixel and the second pixel based on the first weight and the second weight.

公开(公告)号：US12034963B2

公开(公告)日：2024-07-09

申请号：US17731470

申请日：2022-04-28

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  James Bankoski ,  Yue Chen ,  Yuxin Liu ,  Sarah Parker

IPC: H04N11/02 ,  H04N19/105 ,  H04N19/136 ,  H04N19/139 ,  H04N19/176 ,  H04N19/182 ,  H04N19/46 ,  H04N19/517

CPC classification number: H04N19/517 ,  H04N19/105 ,  H04N19/136 ,  H04N19/139 ,  H04N19/176 ,  H04N19/182 ,  H04N19/46

Abstract: Generating a compound predictor block for a current block of video includes generating, for the current block, a first predictor block using one of inter-prediction or intra-prediction and generating a second predictor block. The first predictor block includes a first pixel and the second predictor block includes a second pixel that is co-located with the first pixel. A first weight is determined for the first pixel using a difference between a value of the first pixel and a value of the second pixel. A second weight is determined for the second pixel using the first weight. The compound predictor block is generated by combining the first predictor block and the second predictor block. The compound predictor block includes a weighted pixel that is determined using a weighted sum of the first pixel and the second pixel using the first weight and the second weight.

公开(公告)号：US20240098280A1

公开(公告)日：2024-03-21

申请号：US18272862

申请日：2021-01-19

Applicant: Google LLC

Inventor： Urvang Joshi ,  Yue Chen ,  Sarah Parker ,  Elliott Karpilovsky ,  Debargha Mukherjee

IPC: H04N19/176 ,  H04N19/30

CPC classification number: H04N19/176 ,  H04N19/30

Abstract: Image coding using guided machine learning restoration may include obtaining reconstructed frame data by decoding, obtaining a restored frame by restoring the reconstructed frame, and outputting the restored frame. Obtaining the restored frame may include obtaining a reconstructed block, obtaining guide parameter values, obtaining a restored block, and including the restored block in the restored frame. Obtaining the restored block may include inputting the reconstructed block to an input layer of a trained guided convolutional neural network, wherein the neural network is constrained such that an output layer has a defined cardinality of channels, obtaining, from the output layer, neural network output channel predictions, obtaining a guided neural network prediction as a linear combination of the guide parameter values and the neural network output channel predictions, and generating the restored block using the guided neural network prediction.

公开(公告)号：US20210409705A1

公开(公告)日：2021-12-30

申请号：US16912767

申请日：2020-06-26

Applicant: GOOGLE LLC

Inventor： Sarah Parker ,  Debargha Mukherjee ,  Yue Chen ,  Elliott Karpilovsky ,  Urvang Joshi

IPC: H04N19/119 ,  H04N19/12 ,  H04N19/61 ,  H04N19/176 ,  G06N20/00

Abstract: Transform-level partitioning of a prediction residual block is performed to improve compression efficiency of video data. During encoding, a prediction residual block is generated responsive to prediction-level partitioning performed against a video block, a transform block partition type to use is determined based on the prediction residual block, a non-recursive transform-level partitioning is performed against the prediction residual block according to the transform block partition type, and transform blocks generated as a result of the transform-level partitioning are encoded to a bitstream. During decoding, a symbol representative of the transform block partition type used to encode transform blocks is derived from the bitstream, inverse transformed blocks are produced by inverse transforming encoded video data associated with the prediction residual block, and the prediction residual block is reproduced according to the transform block partition type and used to reconstruct the video block, which is output within an output video stream.

公开(公告)号：US10567793B2

公开(公告)日：2020-02-18

申请号：US15174223

申请日：2016-06-06

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Yue Chen

IPC: H04N19/567 ,  H04N19/176 ,  H04N19/119 ,  H04N19/107 ,  H04N19/157 ,  H04N19/182 ,  H04N19/583

Abstract: Encoding frames of a video stream may include encoding a current block of a current frame, generating a base prediction block for the current block based on current prediction parameters associated with the current block, identifying adjacent prediction parameters used for encoding previously encoded adjacent blocks that are adjacent to the current block. At least one side of the current block is adjacent to two or more of the previously encoded adjacent blocks. The encoding may include determining overlap regions in the current block, each of the overlap regions corresponding to a respective previously encoded adjacent block, generating an overlapped prediction of pixel values for each of the overlap regions according to a weighted function of the base prediction and a prediction based on the adjacent prediction parameters. The weighted function may be based on a difference between the current prediction parameters and the adjacent prediction parameters.

公开(公告)号：US10432972B2

公开(公告)日：2019-10-01

申请号：US15297603

申请日：2016-10-19

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Yue Chen ,  Aamir Anis

IPC: H04N19/65 ,  H04N19/184 ,  H04N19/172 ,  H04N19/182 ,  H04N19/176 ,  H04N19/46 ,  H04N19/117 ,  H04N19/154 ,  H04N19/174 ,  H04N19/82 ,  H04N19/136

Abstract: Reducing error in a reconstructed frame is described. Pixels of the frame are classified into classes based on a classification scheme. Offset values for each class of at least some of the classes are determined, and a respective offset value for a class is applied to each pixel of the class, resulting in offset-adjusted pixels for the class. For the classes, a respective error rate reduction in using the respective offset value for a class as compared to omitting the respective offset value is determined, where the respective error rate reduction is based on the pixels of the class in the reconstructed frame, the offset-adjusted pixels of the class, and co-located source pixels in a source frame decoded to generate the reconstructed frame. A subset of classes is selected for reducing error in the reconstructed frame based on the error rate reductions.

公开(公告)号：US10277897B1

公开(公告)日：2019-04-30

申请号：US15397083

申请日：2017-01-03

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Aamir Anis ,  Yue Chen

IPC: H04N7/12 ,  H04N11/02 ,  H04N11/04 ,  H04N19/117 ,  H04N19/172 ,  H04N19/184 ,  H04N19/182

Abstract: Filtering for a reconstructed frame is described. An initial reconstructed frame is determined from an encoded video bitstream, a subset of filter parameters is decoded from the encoded video bitstream for the initial reconstructed frame, a filter set is determined from the subset of filter parameters based on a relationship between the filter set and the subset of filter parameters, and a final reconstructed frame is generated by applying at least one filter from the filter set to the initial reconstructed frame.