Abstract: Methods and apparatuses are described to encoded data into a bitstream and to decode data from a bitstream. A decoding method including: receiving a bitstream including encoded data of an input signal and a first parameter; parsing the bitstream to obtain the first parameter; obtaining an entropy coding parameter based on the first parameter; reconstructing at least a portion of the input signal, based on the entropy coding parameter and the encoded data. Due to adaptiveness of the entropy coding parameters, the optimal work of the entropy coder is possible on low bitrates which results in the bitrate saving; and the absence of clipping effect is achieved on high bitrates, which results in higher reconstruction signal quality.

Abstract: The present disclosure relates to methods and apparatuses for encoding video data into a bitstream and for decoding video data received in a bitstream. A second control flag indicating whether or not to use multi-hypothesis prediction for intra and inter mode is generated and transmitted only conditionally, upon a determination whether or not separate merge list technique for subblock merge candidates is used. On the other hand, a decoder is capable of deciding usage of multi-hypothesis prediction for intra and inter mode and separate merge list technique for subblock merge candidates even though the second control flag is transmitted only conditionally.

Abstract: A method for inverse quantization of a current block of a picture, the method comprising: receiving a bitstream; obtaining a joint chrominance component residual, JCCR, control flag from the bitstream; obtaining a chrominance mapping information from the bitstream based on the JCCR control flag; obtaining at least one chrominance quantization parameter, QP, offset from the bitstream based on the JCCR control flag; obtaining a QP value for the current chrominance block based on the obtained chrominance mapping information and the at least one obtained chrominance QP offset; performing inverse quantization on the current chrominance block by using the obtained QP value.

Abstract: A method of obtaining a chrominance quantization parameter (QP) for chrominance components based on a luminance QP for luminance component, wherein the method is performed by a decoder, comprising parsing a received bitstream to obtain the luminance QP and information of a mapping function (ƒ) which associates a QP index (QPi) to the chrominance QP (QPc); obtaining the QPi based at least in a part on the luminance QP; obtaining the mapping function based on the obtained information; and obtaining a QPc based on the obtained mapping function and the obtained QPi.

Abstract: The present disclosure relates to methods and apparatuses for encoding video data into a bitstream and for decoding video data received in a bitstream. A second control flag indicating whether or not to use multi-hypothesis prediction for intra and inter mode is generated and transmitted only conditionally, upon a determination whether or not separate merge list technique for subblock merge candidates is used. On the other hand, a decoder is capable of deciding usage of multi-hypothesis prediction for intra and inter mode and separate merge list technique for subblock merge candidates even though the second control flag is transmitted only conditionally.

Abstract: The present disclosure relates to a method of operating a neural network with clipped input data. The method includes defining lower and upper threshold values for integer numbers in data entities of input data for at least one neural network layer. If a value of an integer number in a data entity of the input data is smaller than the defined lower threshold value, the method includes clipping the value of the integer number comprised in the data entity of the input data to the defined lower threshold value. If a value of an integer number in a data entity of the input data is larger than the defined upper threshold value, the method includes clipping the value of the integer number comprised in the data entity of the input data to the defined upper threshold value. Integer overflow of an accumulator register is thereby avoided.

Abstract: A neural network including at least one neural network layer and an activation function connected to an output of the at least one neural network layer. The activation function is implemented as an approximation function of a mathematically defined real valued non-linear activation function, wherein the approximation function allows for integer-only processing of fixed-point representations of input values of the approximation function.

Abstract: A method of operating a neural network based on conditioned weights includes defining integer lower and upper threshold values for values of integer numbers comprised in data entities of input data for the neural network layer. If a value of an integer numbers comprised in a data entity of the input data is smaller than the lower threshold value, the value of the integer number comprised in the data entity of the input data is clipped to the lower threshold value, or if a value of an integer number comprised in a data entity of the input data is larger than the upper threshold value, the value of the integer number comprised in the data entity of the input data is clipped to the upper threshold value. Integer valued weights are determined based on the lower threshold value, the upper threshold value, and a pre-defined accumulator register size, such that integer overflow of the accumulator register can be avoided.

Abstract: A prediction method for an image block comprising a first prediction sub-block and a second prediction sub-block, the prediction method comprising: parsing a first index from a bitstream, wherein the first index is used to obtain prediction information of the first prediction sub-block; parsing a second index from the bitstream; comparing the first index with the second index; adjusting the second index in the event that the second index is equal to or greater than the first index; and obtaining prediction information of the second prediction sub-block according to the adjusted second index.

Abstract: A method of processing a current object is provided. A set of input data tensors representing the current object are inputted into a first neural layer of a transformer based neural network. Based on information about processing the current object, at least one auxiliary data tensor is inputted into the first neural layer or a second neural layer of the transformer based neural network, where the at least one auxiliary data tensor is different from each of the input data tensors of the set of input data tensors and represents at least one auxiliary input. The set of input data tensors are processed by the transformer based neural network using the at least one auxiliary data tensor in order to obtain a set of output data tensors.

Abstract: A method of obtaining a chrominance quantization parameter (QP) for chrominance components based on a luminance QP for luminance component, wherein the method is performed by a decoder, comprising parsing a received bitstream to obtain the luminance QP and information of a mapping function (ƒ) which associates a QP index (QPi) to the chrominance QP (QPc); obtaining the QPi based at least in a part on the luminance QP; obtaining the mapping function based on the obtained information; and obtaining a QPc based on the obtained mapping function and the obtained QPi.

Abstract: The present disclosure relates to video encoding and decoding, and in particular to determining motion information for a current block using a history-based motion vector predictor, HMVP, list. The HMVP list is constructed, with said list being an ordered list of N HMVP candidates Hk, k=0, . . . , N?1, which are associated with motion information of N preceding blocks of the frame and precede the current block. Each HMVP candidate has motion information including elements of one or more motion vectors, MVs, one or more reference picture indices corresponding to the MVs, and one or more bi-prediction weight indices. One or more HMVP candidates from the HMVP list are added into a motion information candidate list for the current block; and the motion information is derived based on the motion information candidate list.

Abstract: A method for inverse quantization of a current block of a picture or a frame, where the method is performed by a decoder, and includes obtaining, by a decoder, from a bitstream, a joint chrominance residual (JCCR) mode for a current block of a picture or a frame, obtaining one or more quantization parameter (QP) offset values for chrominance components from the bitstream, determining at least one QP value for the current block depending on the JCCR mode, and performing an inverse quantization process on a chrominance component of the current block using the determined QP value.

Abstract: A method related to adaptive usage of pixel-based and block-based affine motion compensation and includes performing sub-block-based affine transform prediction on an affine block with a first sub-block size if the first sub-block size is greater than or equal to a first sub-block size threshold. If the first sub-block size is less than the first sub-block size threshold, it is determined whether a pixel-based motion vector field is not applied for performing motion compensation for the affine block. If the motion vector field is not applied, a sub-block-based affine motion prediction is performed with a second sub-block size that is based on the first sub-block size. If the pixel-based motion vector field is applied, motion compensation is performed for a sub-block of the affine block using the pixel-based motion vector field.

Abstract: The present disclosure relates to encoding and decoding of video images. Motion vectors are used for prediction of an image for a current coding unit, which is within a current coding tree unit. The motion vectors are taken from a list of motion vector candidates. The list is generated for the current coding unit using a pattern of positions of allowed motion vectors, and in dependence on the positions of the pattern relative to the current coding unit, and on the position of the current coding unit within the current coding tree unit. From the pattern, a subset of positions is selected and positions are restricted to positions within the current coding tree unit, while other pattern positions not available or not stored in a buffer are excluded. Other excluded pattern positions may be substituted and/or adjusted to as to become available and/or are being stored in the buffer.

Abstract: This application provides methods and apparatuses for encoding image or video related data into a bitstream. 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. A neural network (generalized difference) is applied to a signal and a predicted signal during the encoding to obtain a generalized residual. During the decoding another neural network (generalized sum) may be applied to a reconstructed generalized residual and the predicted signal to obtain a reconstructed signal.

Abstract: The present disclosure relates to encoding and decoding of video images. Motion vectors are used as predictors for prediction of an image for a current coding unit CU, which is within a current coding tree unit CTU. The motion vectors are taken from a list of motion vector candidates MVCs. The list is generated for the current CU using a pattern of positions of allowed motion vectors, and in dependence on the positions of the pattern relative to the current CU, and on the position of the current CU within the current CTU. From the pattern, a subset of positions is selected and positions are restricted to positions within the current CTU, while other pattern positions not available or not stored in a buffer are excluded. Other excluded pattern positions may be substituted and/or adjusted to as to become available and/or are being stored in the buffer.

Abstract: Motion vectors (MVs) are used as predictors for prediction of an image for a current coding unit (CU) within a current video frame. The MVs are from a list of motion vector candidates (MVCs), which is generated. The list includes MVs determined from a first or second pattern, each pattern specifying MVC positions. The first MV positions are within a current video frame, while the second MV positions are for a video frame different from the current frame. The MVC list is generated for a current CU with the MV positions being relative to a position of the current CU. In particular, the MVC list is generated in dependence on a size of the current CU and a size of a grid specifying a minimum distance between two MV positions. One or more MVs as specified by the MV positions of said pattern are included into the MVC list.

Abstract: Reference picture management scheme is provided in the context of video coding. A method of decoding an encoded video sequence, comprising obtaining a value of a reference picture list (RPL) syntax element from a bitstream of the encoded video sequence, the RPL syntax element specifying whether syntax elements related to reference picture lists are present in the bitstream, when the RPL syntax element specifies that the syntax elements related to the reference picture lists are present in the bitstream, obtaining, from the bitstream, values of the syntax elements related to the reference picture lists; and constructing at least one reference picture list for inter prediction using the obtained values of the syntax elements related to the reference picture lists.

Abstract: A method of coding implemented by a decoding/encoding device for coding video data includes for a block coded in affine mode, determining control point motion vectors (CPMVs); determining a reference area in a reference picture corresponding to a sub-block of the affine coded block based on the CPMVs; setting a variable clipMVX equal to TRUE if a size of the reference area is greater than a predefined threshold, otherwise setting a variable clipMVX equal to FALSE; deriving a pixel-based motion vector field for the affine coded block; wherein, if the variable clipMVX is equal to TRUE, the deriving the pixel-based motion vector field further comprises motion vector clipping based on a first clipping range, wherein the first clipping range is determined based on the determined CPMVs and a size of the affine coded block.