Abstract: The present disclosure provides systems and methods for image filtering. The method may include obtaining an initial image block from a reconstructed image; determining at least one candidate image block by performing a filtering operation on the initial image block using at least one trained machine learning model; and determining a target image block based on the at least one candidate image block.

Abstract: The present disclosure may relate to systems and methods for inter frame prediction of a video. A method may include setting, based on a block to be predicted of an image frame, a search template. The method may also include searching for, based on a search strategy, an optimal search block of the search template in a reference frame of the image frame. The method may further include determining, based on the optimal search block, prediction information of the block to be predicted.

Abstract: An intra prediction system is provided. The system may determine a coding unit in an image, the coding unit including a plurality of pixels. The system may determine at least one first reference line and at least one second reference line associated with the coding unit. For each of the plurality of pixels in the coding unit, the system may determine a target predicted value of the pixel based on the at least one first reference line and the at least one second reference line according to a prediction mode. The system may determine a predicted coding unit corresponding to the coding unit based on a plurality of target predicted values of the plurality of pixels in the coding unit.

Abstract: The present disclosure relates to systems and methods for video encoding. The systems may determine a current string in a coding unit (CU) of an image frame. The current string may include one or more pixels. The systems may determine a first cost based on pixels with a same pixel value in the current string. The systems may determine a second cost based on one or more strings that are located above the current string. The systems may further determine a prediction string of the current string based on the first cost and the second cost. To determine the prediction string of the current string based on the first cost and the second cost, the systems may designate the current string as the prediction string of the current string in response to that the first cost and the second cost are not determined.

Abstract: The present disclosure relates to systems and methods for video encoding. The systems may determine a current string in a coding unit (CU) of an image frame. The current string may include one or more pixels. The systems may determine, based on a first pixel in the current string, a reference matching pixel of the first pixel by searching a searching area. The searching area may include a plurality of matching pixels The systems may determine, based on the reference matching pixel and matching patterns, a count of matching pixels in each of a plurality of groups, corresponding to the matching patterns, of the current string. The systems may further determine, based on counts of matching pixels in the plurality of groups corresponding to the matching patterns, a target prediction of the current string.

Abstract: The present disclosure relates to systems and methods for inter prediction based on a Merge mode. The methods may include determining whether a current block in an image frame satisfies a division condition, and in response to determining that the current block satisfies the division condition, obtaining two sub-blocks by dividing the current block according to a division mode. The division mode may include a rectangular division. The methods may further include determine, based on the two sub-blocks, a prediction result of the current block.

Abstract: The present disclosure is related to systems and methods for transformation based on an intra block copy (IBC) mode. The method includes obtaining a set of candidate transformation results by performing a set of candidate transformation modes on a first block in an image. The set of candidate transformation modes include at least one of a first transformation mode, a secondary transformation mode, or a sub-block transformation mode. The method includes determining a target transformation mode for the first block based on the set of candidate transformation results.

Abstract: The present disclosure relates to systems and methods for image compensation. The systems may obtain a reconstructed image frame. The systems may determine a primary classification manner of pixels in the reconstructed image frame. The systems may determine a primary compensation value of each category of pixels in the reconstructed image frame that are classified based on the primary classification manner. The systems may obtain a compensated image frame by compensating the reconstructed image frame based on the primary compensation value of each category of pixels in the reconstructed image frame.

Abstract: The present disclosure relates to systems and methods for block division and encoding in video processing. A method may include obtaining a block to be predicted in an image frame. The method may also include determining, based on a plurality of division modes of the block, a target division mode of the block. The plurality of division modes may include an equal division mode that is configured to divide the block into multiple sub-blocks with a same size. The method may further include dividing, based on the target division mode, the block into a plurality of sub-blocks, and encoding the block based on the plurality of sub-blocks.

Abstract: The present disclosure may relate to a system and a method for video coding. The method may include determining at least one classification mode of a first component of a first pixel for a block in an image frame based on at least one pixel value of at least one second component of at least one second pixel that surrounds the first pixel. The method may also include generating a target classification result by classifying the first component based on at least a portion of the at least one classification mode. The method may also include compensating the first component based on an optimal compensation value of the target classification result.

Abstract: The present disclosure relates to systems and methods for image prediction in video processing. A method may include obtaining a target block that has been predicted in an image frame. The method may also include determining, from the target block, one or more target regions to be compensated. The one or more target regions may be adjacent to at least one boundary of the target block. Each of the one or more target regions may have a predictive value. The method may further include, for a target region of the one or more target regions, determining an updated predictive value of the target region based on the predictive value of the target region and pixel values of pixels in a reference region corresponding to the target region.

Abstract: The present disclosure relates to systems and methods for intra prediction. The methods may include obtaining a current chroma block; obtaining a plurality of luma prediction modes, wherein the plurality of luma prediction modes includes prediction modes at a plurality of positions of a luma block associated with the current chroma block; and selecting a luma prediction mode from the plurality of luma prediction modes as a candidate chroma prediction mode for predicting samples of the current chroma block.

Abstract: A method for processing an online video stream may include determining a transmission performance of a network for a queue of video frames, wherein each video frame in the queue may be associated with a priority level. The method may also include determining a maximum discarding level based on the transmission performance of the network. The method may further include removing a target video frame of which the associated priority level is lower than or equal to the maximum discarding level from the queue.

Abstract: A method for intra-prediction is provided, including: determining at least one reference line of a current coding block, each of the at least one reference line comprising a plurality of first reference pixels; down-sampling the at least one reference line and obtaining a plurality of second reference pixels; performing matrix multiplication for the plurality of second reference pixels and obtaining a reference matrix; and obtaining a matrix-based intra-prediction block of the current coding block based on the reference matrix and the plurality of first reference pixels, the matrix-based intra-prediction block comprising a plurality of first pixels and a plurality of second pixels, a value of each of the first pixels is a value of a corresponding pixel in the reference matrix, and a value of each of the second pixels is obtained based on values of the first pixels and values of the first reference pixels.

Abstract: The present provides an affine prediction method and related devices. The method may include: dividing a current coding block into multiple sub-blocks, and determining an initial prediction value of all pixels in each of the sub-blocks; dividing each of the sub-blocks into multiple fraction blocks, wherein at least one of the fraction blocks comprises at least two integer pixels; determining a motion vector difference and a gradient of each of the fraction blocks; calculating a pixel compensation value of each of the fraction blocks based on the motion vector difference value and the gradient; taking the pixel compensation value of each of the fraction blocks as a pixel compensation value of all pixels in each of the fraction blocks; and calculating a final prediction value of each pixel in the current coding block by the initial prediction value of each pixel and the pixel compensation value.

Abstract: The present disclosure relates to a motion vector prediction method, a video coding method, and related apparatuses and devices. The motion vector prediction method includes: acquiring a candidate list of a current coding block in a preset prediction mode, where the candidate list includes a plurality of candidate motion vectors; performing a motion search of the plurality of candidate motion vectors in the candidate list to obtain an initial optimal motion vector of the current coding block in the preset prediction mode; performing motion compensation on the initial optimal motion vector by using each of a first preset number of pixel accuracies, to determine a final optimal motion vector of the current coding block, where the preset prediction mode comprises any one of a plurality of prediction modes, and pixel accuracies used in any one of the prediction modes are identical.

Abstract: A linear model (LM) prediction method and a coder are disclosed. The method includes dividing a current coding block into at least two sub-blocks; for each of the sub-blocks, constructing a linear model, wherein parameters of the linear model are calculated by using pixel values of adjacent reconstructed pixels of the sub-block and adjacent reconstructed pixels of a reference sub-block of the sub-block; and predicting the sub-block by using the linear model, and obtaining a LM prediction value of the sub-block.

Abstract: An intra frame and inter frame joint prediction method is provided. The method includes determining at least one joint intra frame prediction mode of current coding block based on intra frame prediction mode of at least one encoded block of current frame, or determining the at least one joint intra frame prediction mode of the current coding block based on content characteristics of the current coding block, or taking at least one first specified intra frame prediction mode as the at least one joint intra frame prediction mode of current coding block; obtaining a joint intra frame prediction value of the current coding block based on the at least one joint intra frame prediction mode; and obtaining at least one intra frame and inter frame joint prediction value based on at least one candidate motion vector and the joint intra frame prediction value of the current coding block.

Abstract: An inter-frame prediction method based on a merge with motion vector difference (MMVD) mode may include: constructing a first candidate list of a current coding block in the MMVD mode, wherein the first candidate list includes a first preset number of first candidate motion vectors (MVs); determining a second preset number of motion search amplitudes and a third preset number of motion search directions; taking the first candidate MV as a starting point, and searching by different motion combinations of the motion search amplitudes and the motion search directions, to obtain a MV offset of the first candidate MV under the different motion combinations, for each of the first candidate MVs; determining to obtain an optimal MV of the current coding block based on the MV offset of each of the first candidate MVs in the different motion combinations.

Abstract: An affine prediction method, a computing device and a non-transitory storage medium are disclosed. The method includes obtaining a current coding block comprising a plurality of sub-blocks arranged in an array; dividing the current coding block into at least two areas, wherein each area of the at least two areas comprises two or more of the sub-blocks; setting a corresponding control point motion vector (CPMV) for one or more control points in the each area, respectively; and affine-predicting motion vectors (MVs) of the two or more of the sub-blocks in the each area, using the corresponding CPMV.