Guided restoration of video data using neural networks

    公开(公告)号:US11282172B2

    公开(公告)日:2022-03-22

    申请号:US16515226

    申请日:2019-07-18

    Applicant: GOOGLE LLC

    Abstract: Guided restoration is used to restore video data degraded from a video frame. The video frame is divided into restoration units (RUs) which each correspond to one or more blocks of the video frame. Restoration schemes are selected for each RU. The restoration schemes may indicate to use one of a plurality of neural networks trained for the guided restoration. Alternatively, the restoration schemes may indicate to use a neural network and a filter-based restoration tool. The video frame is then restored by processing each RU according to the respective selected restoration scheme. During encoding, the restored video frame is encoded to an output bitstream, and the use of the selected restoration schemes may be signaled within the output bitstream. During decoding, the restored video frame is output to an output video stream.

    COMPOUND PREDICTION FOR VIDEO CODING

    公开(公告)号:US20210037254A1

    公开(公告)日:2021-02-04

    申请号:US17073892

    申请日:2020-10-19

    Applicant: GOOGLE LLC

    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.

    IMAGE AND VIDEO CODING USING MACHINE LEARNING PREDICTION CODING MODELS

    公开(公告)号:US20200186796A1

    公开(公告)日:2020-06-11

    申请号:US16295176

    申请日:2019-03-07

    Applicant: GOOGLE LLC

    Abstract: Video coding may include generating, by a processor, a decoded frame by decoding a current frame from an encoded bitstream and outputting a reconstructed frame based on the decoded frame. Decoding includes identifying a current encoded block from the current frame, identifying a prediction coding model for the current block, wherein the prediction coding model is a machine learning prediction coding model from a plurality of machine learning prediction coding models, identifying reference values for decoding the current block based on the prediction coding model, obtaining prediction values based on the prediction coding model and the reference values, generating a decoded block corresponding to the current encoded block based on the prediction values, and including the decoded block in the decoded frame.

    GUIDED RESTORATION OF VIDEO DATA USING NEURAL NETWORKS

    公开(公告)号:US20200184603A1

    公开(公告)日:2020-06-11

    申请号:US16515226

    申请日:2019-07-18

    Applicant: GOOGLE LLC

    Abstract: Guided restoration is used to restore video data degraded from a video frame. The video frame is divided into restoration units (RUs) which each correspond to one or more blocks of the video frame. Restoration schemes are selected for each RU. The restoration schemes may indicate to use one of a plurality of neural networks trained for the guided restoration. Alternatively, the restoration schemes may indicate to use a neural network and a filter-based restoration tool. The video frame is then restored by processing each RU according to the respective selected restoration scheme. During encoding, the restored video frame is encoded to an output bitstream, and the use of the selected restoration schemes may be signaled within the output bitstream. During decoding, the restored video frame is output to an output video stream.

    Non-causal overlapped block prediction in variable block size video coding

    公开(公告)号:US10419777B2

    公开(公告)日:2019-09-17

    申请号:US15387797

    申请日:2016-12-22

    Applicant: GOOGLE LLC

    Abstract: A method for processing a selected portion of a video, the selected portion of the video having a plurality of blocks. The method includes obtaining current prediction parameters for all of a plurality of adjacent blocks from the plurality of blocks that are adjacent to a current block from the plurality of blocks in the selected portion of the video, generating a base prediction for the current block from the plurality of blocks using the current prediction parameters associated with the current block, identifying adjacent prediction parameters from the current prediction parameters for a first adjacent block from the plurality of adjacent blocks, determining an overlap region within the current block and adjacent to the first adjacent block, and generating, for each pixel within the overlap region, an overlapped prediction for the pixel as a function of the base prediction and a prediction based on the adjacent prediction parameters.

    Adaptive overlapped block prediction in variable block size video coding

    公开(公告)号:US10390033B2

    公开(公告)日:2019-08-20

    申请号:US15173881

    申请日:2016-06-06

    Applicant: GOOGLE LLC

    Abstract: Decoding a current block of an encoded video stream may include 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 decoding a previously decoded adjacent block that is adjacent to the current block, and determining an overlap region within the current block and adjacent to the adjacent block. The overlap region has a size being determined as a function of a difference between the first prediction parameters and the adjacent prediction parameters. For each pixel within the overlap region, an overlapped prediction of a pixel value may be generated as a function of the base prediction and a prediction based on the adjacent prediction parameters.

    Warped Motion Compensation With Explicitly Signaled Extended Rotations

    公开(公告)号:US20240388690A1

    公开(公告)日:2024-11-21

    申请号:US18576733

    申请日:2021-07-15

    Applicant: Google LLC

    Abstract: Video coding using warped motion compensation is described. Extended rotations for the warped motion compensation can be explicitly signaled. For example, motion parameters for predicting the current block and a rotation angle can be decoded. A warping matrix is obtained using the motion parameters and the rotation angle, and a prediction block is obtained by projecting the current block to a quadrilateral in a reference frame. Also described is determining a prediction model of the current block and obtaining a prediction block by projecting the current block to a quadrilateral in a reference frame. Determining the prediction model can include determining whether to predict the current block using a motion vector, a local warping model, or a global motion model, obtaining motion parameters of the prediction model, decoding a rotation angle, and obtaining a warping matrix using the motion parameters and the rotation angle.

    Restoration in video coding using domain transform recursive filters

    公开(公告)号:US10757408B2

    公开(公告)日:2020-08-25

    申请号:US15789400

    申请日:2017-10-20

    Applicant: GOOGLE LLC

    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.

Patent Agency Ranking