Abstract: The present disclosure relates to picture encoding and decoding of image regions on tile-basis. In particular, multiple components of an input tensor including a first and second component in spatial dimensions is processed within multiple pipelines. The processing of the first component includes dividing the first component in the spatial dimensions into a first plurality of tiles. Likewise, the processing of the second component includes dividing the second component in the spatial dimensions into a second plurality of tiles. The respective first and second plurality of tiles are then processed each separately. Among the first and second plurality of tiles there are at least two respective collocated tiles differing in size. In case of compression, the processing of the first and/or second component includes picture encoding, rate distortion optimization quantization, and picture filtering. In case of decompression, the processing includes picture decoding and picture filtering.

Abstract: Neural-network-based picture encoding and decoding of image regions may be performed on a tile-basis. An input tensor representing picture data is processed by the neural network, which includes at least a first and second subnetwork. The first subnetwork is applied to a first tensor where the first tensor is divided in a spatial dimensions into a first plurality of tiles. The first tiles are then further processed by the first subnetwork. After application of the first subnetwork, the second subnetwork is applied to a second tensor where the second tensor is divided in the spatial dimensions into a second plurality of tiles. The second tiles are then further processed by the second subnetwork. Among the first and second plurality of tiles there are at least two respective collocated tiles differing in size.

Abstract: Embodiments of this application provide a method for processing image signal conversion, including: obtaining a primary color component of a to-be-processed pixel; and converting a first value of the primary color component into a second value based on a preset dynamic range conversion model, where the dynamic range conversion model is: L ? = F ? ( L ) = a × ( p × L n ( k 1 × p - k 2 ) × L n + k 3 ) m + b , where L is the first value, L? is the second value, and k1, k2, k3, a, b, m, n, and p are model parameters.

Abstract: For picture decoding and encoding of neural-network-based bitstreams, a picture is represented by an input set of samples which is obtained from the bitstream. The picture is reconstructed from output subsets, which are generated as a result of processing the input set L. The input set is divided into multiple input subsets Li. The input subsets are each subject to processing with a neural network having one or more layers. The neural network uses as input multiple samples of an input subset and generates one sample of an output subset. By combining the output subsets, the picture is reconstructed. In particular, the size of at least one input subset is smaller than a size that is required to obtain the size of the respective output subset, after processing by the one or more layers of the neural network.

Abstract: A method of filtering a sample value of a picture and a video decoding apparatus are disclosed, the method comprises: obtaining a reconstructed sample value for a block of the picture; obtaining filter coefficients for adaptive loop filtering according to a bitstream; obtaining a sum value according to the filter coefficients and the reconstructed sample value for the block; rounding the sum value according to a vertical position of a sample in the block, to obtain a rounded sum value; obtaining a filter reconstructed sample value for the block according to the rounded sum value.

Abstract: A method and device for digital signal processing are provided, particularly relating to video image processing. The device obtains image data comprising a plurality of pixels. The image data comprises a plurality of sequentially captured images. The device estimates, for a target image, a set of backward motion vector fields (backward MVFs) based on the target image, and a first set of images captured before the target image. The device further estimates a set of forward MVFs based on the target image and a second set of images captured after the target image. Depending on the estimating for the target image, the device generates an output image based on a merging procedure of the target image and the first set of images and the set of backward MVFs, and/or the second set of images and the set of forward MVFs.

Abstract: A method of decoding of a video or picture bitstream implemented by a decoding device, the bitstream including a current sequence parameter set (SPS) comprising syntax elements that apply to a video sequence, the method comprising: obtaining a first syntax element used to determine a maximum number of temporal sublayers that is allowed to be present in each coded layer video sequence) referring to the current SPS, wherein a value of the first syntax element is in a range of 0 to a first value, wherein the first value is a value of a second syntax element used to determine the maximum number of temporal sublayers that is allowed to present in a layer in each coded video sequence referring to a video parameter set, when the second syntax element is referred to by the SPS; decoding the bitstream based on the value of the first syntax element.

Abstract: A method of decoding of a picture from a video bitstream is disclosed. The video bitstream includes a slice header of a current slice and data representing the current slice. The method comprises: obtaining a parameter used to derive a number of tiles in the current slice from the slice header when a slice address of the current slice is not an address of a last tile in the picture where the current slice located; and reconstructing the current slice using the number of tiles in the current slice and the data representing the current slice.

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 intra prediction of a coding block, performed by a decoder, the method comprising: obtaining a bitstream for the coding block; obtaining a value of intra prediction mode according to the bitstream; obtaining a value of an index for the coding block in accordance with the bitstream; obtaining a set of reference samples for the coding block, the set of reference samples comprises samples of a reconstructed block and additional samples; when the value of the index for the coding block is not equal to the predefined value, the set of reference samples comprises only of samples of the reconstructed block; obtaining a prediction value of a sample comprised in the coding block, according to the value of intra prediction mode for the coding block and the set of reference samples.

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 coding implemented by a decoding device, a decoder, an encoder are disclosed, the method comprising: obtaining a bitstream; obtaining a value of a syntax element sps_num_subpics_minus1 according to parse the bitstream; when the value of the syntax element sps_num_subpics_minus1 is greater than a preset value, obtaining a value of a syntax element sps_independent_subpics_flag from the bitstream.

Abstract: A method of coding implemented by a decoding device is provided. The method includes parsing a bitstream to obtain a flag from a picture header of the bitstream, wherein the flag indicates whether a current picture is I picture. when the flag indicates that the current picture is I picture, a syntax element designed for inter prediction is inferred to a default value; or when the flag indicates that the current picture is P or B picture, obtaining a syntax element designed for inter prediction from the picture header.

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: A method of coding implemented by a decoding device or an encoding device, comprising obtaining indication information for a luma position (cbWidth/2, cbHeight/2) of a current coding block, relative to a top-left luma sample position (xCb, yCb) of the current coding block; setting a value of a luma intra prediction mode associated with the current coding block to a first default value, when the indication information indicates that an Intra Block Copy (IBC) mode or palette mode is applied for the luma component at the luma position (cbWidth/2, cbHeight/2), relative to the top-left luma sample position (xCb, yCb) of the current coding block; and obtaining a value of a chroma intra prediction mode based on the value of the luma intra prediction mode of the current coding block.

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: An image processing apparatus processes a color filter mosaic, CFM, image of a scene into a final image of the scene. The image processing apparatus includes processing circuitry configured to implement a neural network. The neural network is configured to process the CFM image into an enhanced CFM image. The processing circuitry is further configured to transform the enhanced CFM image into the final image.

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.