Abstract: A video coding mechanism is disclosed. The mechanism includes partitioning a picture into a plurality of first level tiles. A subset of the first level tiles is partitioned into a plurality of second level tiles. The first level tiles and the second level tiles are encoded into a bitstream. A split indication is encoded into the bitstream. The split indication indicates that at least one of the first level tiles is split into the second level tiles. The bitstream is stored for communication toward a decoder.

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 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: 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: Methods and apparatuses are provided for estimating motion vectors of a dense motion field based on subsampled sparse motion field. The sparse motion field includes two or more motion vectors with their respective start positions. For each of the motion vectors, a transformation is derived which transforms the motion vector from its start point into a target point. The transformed motion vectors then contribute to the estimated motion vector on the target position. The contribution of each motion vector is weighted. Such motion estimation may be readily used for video encoding and decoding.

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: Methods and apparatuses are provided to approximate a cumulative distribution function (CDF) interval-wise with second order polynomials, while posing constraints on the polynomials within the intervals and/or on the boundary between the intervals. In this manner, a CDF approximation is obtained, which may be used in a variety of applications including entropy encoding and decoding of any source data. The constraints correspond to the characteristics of the CDF to be approximated.

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: A video coding mechanism is disclosed. The mechanism includes partitioning a picture into a plurality of first level tiles. A subset of the first level tiles is partitioned into a plurality of second level tiles. The first level tiles and the second level tiles are assigned into one or more tile groups such that all tiles in an assigned tile group containing the second level tiles are constrained to cover a rectangular region of the picture. The first level tiles and the second level tiles are encoded into a bitstream. The bitstream is stored for communication toward a decoder.

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: A method of video encoding a sequence of pictures, the method being implemented in an encoding device and comprising: obtaining an intra prediction picture comprising at least two sub-units; obtaining a first encoded other picture, wherein the intra prediction picture and the first encoded other picture have the same Picture Order Count, POC, value; obtaining encoded other pictures different from the intra prediction picture and the first encoded other picture; and distributing the at least two sub-units of the intra prediction picture over one or more sub-units of the encoded other pictures and/or over one or more sub-units of the first encoded other picture.

Abstract: A method of coding implemented by an encoding device for encoding video data is disclosed. The method comprises reducing at least part of Least Significant Bits of Picture Order Counter (POC_LSB) in the video data by omitting one bit of the POC_LSB or by omitting a number of bits of the POC_LSB depending on the layer IDs of the video data. The method further includes coding the reduced POC_LSB.

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.

Abstract: A video coding mechanism is disclosed. The mechanism includes partitioning a picture into a plurality of first level tiles. A subset of the first level tiles is partitioned into a plurality of second level tiles. The first level tiles and the second level tiles are encoded into a bitstream. A split indication is encoded into the bitstream. The split indication indicates that at least one of the first level tiles is split into the second level tiles. The bitstream is stored for communication toward a decoder.

Abstract: A method for coding video data is disclosed. The method comprises: obtaining a center motion vector of a coding block; deriving a first motion vector range for the coding block based on the center motion vector and a motion vector spread, wherein the motion vector spread depends on a size of the coding block; if the first motion vector range is at least partially pointing outside a first area including a reference picture, updating the first motion vector range to point within the first area, such that a minimum value or a maximum value of the updated first motion vector range is pointing at a boundary of the first area.

Abstract: An apparatus for inter prediction of a sample value of a current full-integer pixel of a plurality of pixels associated with a current block of a current frame of a video signal is disclosed. The apparatus is configured to: determine a motion vector of the current full-integer pixel based on a motion compensation model; determine for the current full-integer pixel a corresponding sub-integer pixel in a reference frame; determine positions of a set of corresponding filter support pixels in the reference frame; obtain a respective sample value of the corresponding sub-integer pixel of the current full-integer pixel and the corresponding filter support pixels in the reference frame by applying a bilinear interpolation; and determine the inter predicted sample value of the current full-integer pixel.

Abstract: A coding method implemented by a decoding/encoding device for coding video data comprises coding, in a supplemental enhancement information (SEI) message, a set of sequence parameters. The set of sequence parameters is associated with temporal IDs of the sub-layers of a bitstream or coded layer video sequence (C(L)VS). The coding method further comprises processing the bitstream or C(L)VS by using the set of sequence parameters included in the SEI message. The set of sequence parameters is used for deriving or representing a picture rate of the sequence.

Abstract: A video coding mechanism is disclosed. The mechanism includes partitioning a picture into a plurality of first level tiles. A subset of the first level tiles is partitioned into a plurality of second level tiles. The first level tiles and the second level tiles are assigned into one or more tile groups such that all tiles in an assigned tile group containing the second level tiles are constrained to cover a rectangular region of the picture. The first level tiles and the second level tiles are encoded into a bitstream. The bitstream is stored for communication toward a decoder.

Abstract: A method for coding a video implemented in an encoder or a decoder, comprising: determining control point motion vectors, CPMVs, for a block according to affine inter-prediction, according to a preselected affine motion model, the block being an affine block; performing motion compensation for the block using a pixel-based motion vector field according to values of the CPMVs, upon fulfilling at least one of the following conditions: A) for a predefined size of a sub-block of M×M, during processing of one line, respectively, of the sub-block the number of lines of the reference picture is less than N, where N is an integer and N is larger than 2.

Abstract: A video coding mechanism is disclosed. The mechanism includes partitioning a picture into a plurality of first level tiles. A subset of the first level tiles is partitioned into a plurality of second level tiles. Each second level tile contains a single rectangular slice of picture data. The first level tiles and the second level tiles are encoded into a bitstream. The bitstream is stored for communication toward a decoder.