Abstract: The present disclosure provides methods and devices of processing a block according to a merge candidate list, the method comprising: constructing a first list according to motion information of neighboring blocks of a current block; obtaining prediction information of the current block; when the prediction information of the current block indicates that a sub-block prediction is applied to the current block, obtaining a uni-prediction candidate for the current block according to the first list; using, the uni-prediction candidate for the current block to perform inter prediction of the current block. According to embodiment of the present disclosure, the regular merge list can be directly used and there is no need to explicitly generate the uni-prediction merge candidate list for sub-block prediction.

Abstract: The present disclosure relates generally to video coding and picture partitioning methods. In particular, the disclosure is concerned with relations between partition constraint elements, by setting partitioning rules for different picture partitioning methods. The disclosure provides devices and corresponding methods for generating or processing a bitstream including encoded pictures, particularly for setting and including partition constraint element into the bitstream. One of the devices is configured to determine a minimum luma size of a leaf block resulting from quadtree splitting (MinQtSizeY), determine a maximum luma size of a coding block where partitioning using a binary tree splitting is allowed (MaxBtSizeY) based on the MinQtSizeY, and include information for the determined MinQtSizeY into the bitstream.

Abstract: A deblocking filter of an image processing device is provided. The deblocking filter is used in an image coding process, for deblocking a block edge between a first coding block and a second coding block of an image. The first block has SA samples perpendicular to the block edge by N samples parallel to the block edge, and the second block has SB samples perpendicular to the block edge by N samples parallel to the block edge. No more than IA samples of the first coding block are used as first filter input values, and no more than IB samples of the second coding block are used as second filter input values. No more than MA samples of the first coding block are modified as first filter output values, and no more than MB samples of the second coding block are modified as second filter output values.

Abstract: The present disclosure relates to the field of picture processing. Especially, the disclosure deals with improving the prediction of a block of a picture when decoding or encoding. A method of coding a block of a picture, comprising: obtaining an indication parameter for a current coding block. The indication parameter represents whether a multi-hypothesis prediction is applied to the current coding block. When the indication parameter represents that the multi-hypothesis prediction is applied to the current coding block, coding the current coding block according to a planar mode.

Abstract: Apparatuses and methods for encoding and decoding a video are provided. The method includes determining whether at least one of two blocks of an image in a video is predicted with a combined inter-intra prediction (CIIP), where the two blocks include a first block (block Q) and a second block (block P). There is a boundary between the two blocks. The method further includes setting a boundary strength (Bs) for the boundary to a first value when at least one of the two blocks is predicted with the CIIP, and performing deblocking filter based on the Bs.

Abstract: This application provides methods and apparatuses for processing of picture data or picture feature data using a neural network with two or more layers. The present disclosure may be applied in the field of artificial intelligence (AI)-based video or picture compression technologies, and in particular, to the field of neural network-based video compression technologies. According to some embodiments, position within the neural network, at which auxiliary information may be entered for processing is selectable based on a gathering condition. The gathering condition may assess whether some prerequisite is fulfilled. Some of the advantages may include better performance in terms of rate and/or disclosure due to the effect of increased flexibility in neural network configurability.

Abstract: A method of decoding a coded video bitstream implemented by a video decoder. The method includes determining a split mode for a coding tree unit (CTU) in an encoded bitstream, where the split mode is one of triple tree (TT), vertical binary tree (BT), and horizontal BT; marking a coding unit (CU) from the CTU as not to be predicted by intra prediction when one of three conditions is met; parsing the encoded bitstream to obtain a prediction unit and residual information for the CU from the CTU; and reconstructing the CU based on the prediction unit and the residual information when the CU has been marked.

Abstract: A non-transitory computer-readable medium for inter-prediction and an encoder are provided. An initial motion vector is obtained for a current block. Search space positions are determined according to the initial motion vector. Matching costs for the search space positions are checked according to a checking order to select a target search space position with a minimal matching cost. A refining motion vector of the current block is determined based on the initial motion vector and the target search space position. A central search space position is determined according to the checking order, and the central search space position is pointed to by the initial motion vector.

Abstract: A partitioning method comprises determining whether a current block of a picture is a boundary block and whether the size of the current block is larger than a minimum allowed quadtree leaf node size; and if the current block is the boundary block and the size of the current block is not larger than the minimum allowed quadtree leaf node size (MinQTSize), applying forced binary tree (BT) partitioning to the current block. A method comprises making a determination that a current block of a picture is a boundary block and that a size of the current block is less than or equal to a minimum allowed quadtree (QT) leaf node size (MinQTSize); and applying, in response to the determination, forced binary tree (BT) partitioning to the current block.

Abstract: The present disclosure relates to the field of picture processing. Especially, the disclosure deals with improving the prediction of a block of a picture when decoding or encoding. A method of coding a block of a picture, comprising: obtaining an indication parameter for a current coding block. The indication parameter represents whether a multi-hypothesis prediction is applied to the current coding block. When the indication parameter represents that the multi-hypothesis prediction is applied to the current coding block, coding the current coding block according to a planar mode.

Abstract: A method for encoding a picture and decoding a bitstream that represents a picture using a neural network (NN) that comprises a plurality of sub-networks is provided. The method includes applying, before processing an input with the at least one sub-network comprising at least two downsampling layers, a rescaling to the input, wherein the rescaling comprises changing the size S1 in the at least one dimension to be S1 so that S1 is an integer multiple of a combined downsampling ratio Rk of the at least one sub-network, after the rescaling, processing the input by the at least one sub-network comprising at least two downsampling layers and providing an output with the size S2, wherein S2 is smaller than S1, and providing, after processing the picture using the NN, a bitstream as output.

Abstract: Disclosed herein are methods and systems for encoding a picture and decoding a bitstream that may represent an encoded picture. During encoding and decoding, rescaling operations are applied to rescale an input to a size that can be processed by a layer of a neural network. Embodiments disclosed herein provide methods for rescaling that achieve a reduced size of the bitstream, thereby improving compression.

Abstract: A method for deblocking a chroma block edge between a first chroma block of a first image block and a second chroma block of a second image block. The method includes a decision process which includes: determining a first chroma quantization parameter for the first chroma block based on a first luma quantization parameter of a first luma block of the first image block and a chroma QP mapping table for the first chroma block; determining a second chroma quantization parameter for the second chroma block based on a second luma quantization parameter of a second luma block of the second image block and a chroma QP mapping table for the second chroma block; determining an averaged and rounded chroma quantization parameter based on the first chroma quantization parameter and the second chroma quantization parameter; and determining a threshold parameter based on the averaged and rounded chroma quantization parameter.

Abstract: A method of filtering a sample value of a picture is provided, with an integer t that is less than k and with an integer j in the range of 1 to m: generating, with an integer i in the range of 1 to k?t?1, a filtered sample value by applying a filter to the value of the sample p(i,j), wherein the filter is supported by a set of filter support samples, the set of filter support samples does not comprise any samples p(i?,j?) with row index i? greater than k?t?1, and/or generating, with an integer i in the range of k?t to k, a filtered sample value by applying a filter to the value of the sample p(i,j), the filter is supported by a set of filter support samples, wherein the set of filter support samples does not comprise any samples p(i?,j?) with row index i? less than k?t.

Abstract: An image decoding method for decoding a bitstream including a coded signal resulting from coding tiles and slices into which an image is partitioned, the method including decoding the coded signal, wherein each of the slices is either a normal slice having, in a header, information used for an other slice or a dependent slice which is decoded using information included in a slice header of another slice, and when the normal slice starts from a position other than a beginning of a first tile, a second tile coded next to the first tile does not start from the dependent slice.

Abstract: An image includes a plurality of rows of largest coding units (LCUs). Encoding the image includes determining whether or not wavefront parallel processing is enabled, and partitioning the plurality of rows of LCUs to comprise a normal slice and a group of dependent slices. The normal slice includes at least one LCU, and the group of dependent slices includes at least one LCU and consists of every dependent slice that uses information from a slice header of the normal slice for encoding. Based on the determination that wavefront parallel processing is enabled, the partitioning of the plurality of rows of LCUs is restricted such that a last LCU in the group of dependent slices belongs in a same row as a first LCU of the normal slice when the first LCU of the normal slice is not a first LCU of the row.

Abstract: A deblocking method is provided for deblocking a sub-partition boundary within a coding block during image encoding and/or image decoding process. The coding block is coded in an intra prediction mode and the coding block is partitioned into sub-partitions comprising a first sub-partition and a second sub-partition that is adjacent to the first sub-partition. The method comprises: determining a maximum filter length to be 1 for a first/second sub-partition when a width of the first or second sub-partition is 4 samples, or when a height of the first or second sub-partition is 4 samples; modifying a value of up to one sample of the first or second sub-partition, wherein the value of the up to one sample is obtained from a row or a column of the first or second sub-partition that is perpendicular to and adjacent to the sub-partitions boundary between the first sub-partition and the second sub-partition.

Abstract: A deblocking method is provided for deblocking a sub-partition boundary within a coding block during image encoding and/or image decoding process. The coding block is coded in an intra prediction mode and the coding block is partitioned into sub-partitions comprising a first sub-partition and a second sub-partition that is adjacent to the first sub-partition. The method comprises: determining a maximum filter length to be 1 for a first/second sub-partition when a width of the first or second sub-partition is 4 samples, or when a height of the first or second sub-partition is 4 samples; modifying a value of up to one sample of the first or second sub-partition, wherein the value of the up to one sample is obtained from a row or a column of the first or second sub-partition that is perpendicular to and adjacent to the sub-partitions boundary between the first sub-partition and the second sub-partition.

Abstract: A method of intra prediction of a block, comprising obtaining two lines of reconstructed neighboring samples; deriving a set of reference samples based on the two lines of reconstructed neighboring samples; obtaining a set of MIP coefficients based on a intra prediction mode obtained from a bitstream, wherein a MIP coefficient CMIP of the set of MIP coefficients is obtained based on CMIP=vsgn·(q<<s), where q is a magnitude of the MIP coefficient, wherein s is a left shift value and vsgn is a sign value of the MIP coefficient; and obtaining a prediction block based on the set of reference samples and the set of MIP coefficients, wherein a reconstruct picture is obtained based on the prediction block.

Abstract: A deblocking method, for deblocking a transform block boundary within a coding block in an image encoding and/or an image decoding is provided, wherein the coding block comprising transform blocks is coded in inter prediction mode and the transform blocks comprises a first transform block and a second transform block; wherein the method comprises: determining, when the boundary between the first transform block and the second transform block is a transform block boundary and at least one of the first transform block and the second transform block has one or more non-zero transform coefficients, a value of a BS parameter for the boundary between the first transform block and the second transform block to be a first value; and performing de-blocking filtering process to the boundary between the first transform block and the second transform block at least based on the value of the boundary strength parameter.