Abstract: A method, computer program, and computer system is provided for coding video data. Reference samples and magnitudes of transform coefficients corresponding to a current block of video data from an input to a neural network are identified. Sign values associated with the transform coefficients are predicted using neural networks. The video data is encoded/decoded based on the predicted sign values.

Abstract: An example method of video coding includes receiving a video bitstream that includes a plurality of blocks and a plurality of quantized transform coefficients. The method includes deriving a dequantized transform coefficient for a first quantized transform coefficient of the plurality of quantized transform coefficients. The method also includes obtaining an adjusted transform value by applying an offset value to the dequantized transform coefficient, the adjusted transform value based on a quantized transform coefficient level and a current state of dequantization. The method further includes reconstructing a first block using the adjusted transform value.

Abstract: Systems and methods for coding and decoding of a coded bitstream is provided. A method includes encoding a block of a picture. The encoding includes selecting a transform set based on at least one neighboring sample from one or more previously encoded neighboring blocks or from a previously encoded picture and transforming coefficients of the block using a transform from the transform set.

Abstract: Video quality analysis may be used in many multimedia transmission and communication applications, such as encoder optimization, stream selection, and/or video reconstruction. An objective VQA metric that accurately reflects the quality of processed video relative to a source unprocessed video may take into account both spatial measures and temporal, motion-based measures when evaluating the processed video. Temporal measures may include differential motion metrics indicating a difference between a frame difference of a plurality of frames of the processed video relative to that of a corresponding plurality of frames of the source video. In addition, neural networks and deep learning techniques can be used to develop additional improved VQA metrics that take into account both spatial and temporal aspects of the processed and unprocessed videos.

Abstract: An example method of video coding includes receiving a video bitstream for a plurality of blocks. When an extrapolation filter-based intra prediction (EIP) mode is active for a current block of the plurality of blocks, the method also includes determining, when a boundary condition is met for the current block, one or more EIP mode parameters from a first set of EIP parameters. When the boundary condition is not met for the current block, the method also includes determining the one or more EIP mode parameters from a second set of EIP parameters, where the second set of EIP parameters includes one or more parameters not included in the first set of EIP parameters. The method further includes reconstructing the current block using the one or more EIP mode parameters.

Abstract: An example method of video coding includes receiving a video bitstream for a plurality of blocks. The method also includes parsing, from the video bitstream, an indicator indicating that a current block of the plurality of blocks is to be decoded using an extrapolation filter intra prediction (EIP) mode. The method includes identifying transform information for the current block according to an EIP feature, the EIP feature including directionality information associated with the EIP mode and/or an index of the EIP mode; and the method includes generating a transform block for the current block using the transform information.

Abstract: A video bitstream including a current transform block (TB) in a current picture is received. A context model is determined for a syntax element associated with a transform coefficient level of a first coefficient group (CG) in the current TB based on transform coefficient levels of at least one first neighboring CG of the first CG. The first CG is positioned on a first scanning line. The at least one first neighboring CG is positioned on a second scanning line that is scanned before the first scanning line. The context model is a probability model for a non-separable transform. The first CG is reconstructed based on the transform coefficient level that is determined according to the determined the context model.

Abstract: This disclosure relates transform configuration and signaling for a compound inter intra prediction modes. In one example, a method for decoding a video block in a video stream is disclosed. The method may include determining that the video block is predicted in a Compound Inter Intra Prediction (CIIP) mode, wherein the video block is derived as a combination of an intra prediction and an inter prediction in the CIIP mode.

Abstract: This disclosure relates transform configuration and signaling for a compound inter-intra prediction modes. In one example, a method for decoding a video block in a video stream is disclosed. The method may include determining that the current block is predicted under a CIIP mode; generating a set of secondary transform coefficients for the current block from the video bitstream; applying a combined inter intra secondary transform by: performing an inverse separable or non-separable secondary transform on the set of secondary transform coefficients to obtain a set of primary transform coefficients of the current block; and performing an inverse primary transform on the set of primary transform coefficients to obtain a residual block of the current block; and decoding, under the CIIP mode, the current block from the residual block.

Abstract: This disclosure relates generally to video coding and particularly to methods and systems for deriving offsets in cross-component transform coefficient level reconstruction. An example method for decoding a current video block of a video bitstream is disclosed. The method includes receiving a coded video bitstream; extracting, from the coded video bitstream, a first transform coefficient of a first color component for a current video block; determining a second transform coefficient of a second color component for the current video block; deriving an offset value based on at least one of the following: a quantization step size, or the first transform coefficient; adding the offset value to the second transform coefficient to generate a modified second transform coefficient for the second color component; and decoding the current video block based on the first transform coefficient and the modified second transform coefficient of the second color component.

Abstract: This disclosure relates to a harmonized design among multiple reference line intra prediction, transform partitioning, and transform kernels or processing video information. One example method is disclosed. The method includes retrieving a data block of a video frame, the data block having an adjacent reference line and one or more non-adjacent reference lines in the video frame; determining whether one of the one or more non-adjacent reference lines is to be used for intra prediction of the data block. When an adjacent reference line is used for the intra prediction of the data block, selecting a target transform kernel from a first set of transform kernels to transform the data block; and when a non-adjacent reference line is used for the intra prediction of the data block, selecting the target transform kernel from a second set of transform kernels to transform the data block.

Abstract: Methods, apparatus, and computer readable storage medium for implementation of signaling EOC/EOR. The method includes receiving a video bitstream comprising a transform block having two dimensions, the transform block being entropy encoded; determining whether a one-dimensional transform skip is applied to the transform block based on a syntax element in the video bitstream; in response to the one-dimensional transform skip being applied to the transform block, obtaining, from the video bitstream, an end position value associated with the transform block, the end position value indicating only one of a horizontal coordinate end position in the transform block and a vertical coordinate end position in the transform block; and retrieving the transform block from the video bitstream according to the end position value.

Abstract: A method for coding video data, executable by a processor, includes receiving video data; entropy-parsing the received video data into one or more components; de-quantizing the one or more entropy-parsed components; performing a joint component secondary transformation (JCST) on the one or more components in accordance with a JCST kernel selected based on one of (i) a prediction mode corresponding to the video data, (ii) a primary transform type of a current block, and (iii) a secondary transform kernel selected for the current block; and decoding the video data based on one or more residual components corresponding to the joint component secondary transformed components.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data is received. One or more transform cores corresponding to a transform associated with the video data are identified. The one or more transform cores include one or more of a line graph transform (LGT) and a discrete sine transform (DST) The video data is decoded based on the identified transform core. The transform cores correspond to one or more from among an 8-bit transform core and a 10-bit transform core. The transform corresponds to one or more from among a 2-point transform, a 4-point transform, an 8-point transform, and a 16-point transform.

Abstract: This disclosure relates to secondary transform of video blocks with adaptive kernel options. For example, a method for decoding a video block in a video stream is disclosed. The method may include comprising parsing and processing the video stream to generate: a set of secondary transform coefficients associated with the video block; an intra prediction mode associated with the video block; and a kernel index indicating a secondary transform kernel among a group of secondary transform kernels. The method may further include identifying the group of secondary transform kernels based on the intra prediction mode; and performing an inverse secondary transform of the set of secondary transform coefficients to generate primary transform coefficients of the video block based on the secondary transform kernel among the group of secondary transform kernels identified by the kernel index.

Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry for video decoding. The processing circuitry determines a transform candidate for a block in a current picture from a group of transform sets based on one of a feature vector {right arrow over (F)} or a feature scalar S extracted from reconstructed samples in one or more neighboring blocks of the block. Each transform set of the group of transform sets can include one or more transform candidates for the block. The one or more neighboring blocks can be in the current picture or a reconstructed picture different from the current picture. The processing circuitry reconstructs samples of the block based on the determined transform candidate.

Abstract: Systems and methods for coding and decoding of a coded bitstream is provided. A method includes encoding a block of a picture. The encoding includes selecting a transform set based on at least one neighboring sample from one or more previously encoded neighboring blocks or from a previously encoded picture and transforming coefficients of the block using a transform from the transform set.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry. The processing circuitry decodes from a coded video bitstream, transform coefficients associated with a coding block that is a non rectangular partition of a picture. Further, the processing circuitry determines residuals of the coding block based on the transform coefficients, and reconstructs samples of the coding block based on the residuals of the coding block.

Abstract: This disclosure relates generally to video coding and particularly to methods and systems for deriving offsets in cross-component transform coefficient level reconstruction. An example method for decoding a current video block of a video bitstream is disclosed. The method includes receiving a coded video bitstream; extracting, from the coded video bitstream, a first transform coefficient of a first color component for a current video block; determining a second transform coefficient of a second color component for the current video block; deriving an offset value based on at least one of the following: a quantization step size, or the first transform coefficient; adding the offset value to the second transform coefficient to generate a modified second transform coefficient for the second color component; and decoding the current video block based on the first transform coefficient and the modified second transform coefficient of the second color component.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data is received. One or more transform cores corresponding to a transform associated with the video data are identified. The one or more transform cores include one or more of a line graph transform (LGT) and a discrete sine transform (DST) The video data is decoded based on the identified transform core. The transform cores correspond to one or more from among an 8-bit transform core and a 10-bit transform core. The transform corresponds to one or more from among a 2-point transform, a 4-point transform, an 8-point transform, and a 16-point transform.