Abstract: Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that receives a video bitstream including coded residuals of a current block. The processing circuitry determines a plurality of transform coefficients for the current block based on the coded residuals. The processing circuitry calculates, for each of a plurality of sign prediction hypotheses, a cost of the respective sign prediction hypothesis by performing sign prediction on a subset of the plurality of transform coefficients based on a subset of samples in at least one of a topmost row or a leftmost column of the current block. A number of samples in the subset of samples is a constant number. The processing circuitry selects one of the sign prediction hypotheses with a minimal cost. The processing circuitry performs the sign prediction according to the selected sign prediction hypothesis.

Abstract: Aspects of the disclosure provide a method and an apparatus for video coding. In some examples, an apparatus includes processing circuitry that receives a bitstream that includes coded information representing a current bin of a current syntax element of a first syntax element type for a block in a picture. The processing circuitry determines, for the current bin of the current syntax element, a current context model associated with both the first syntax element type and a second syntax element type different from the first syntax element type. The processing circuitry also decodes the coded information according to the current context model to obtain the current bin of the current syntax element, and reconstructs the current block according to a characteristic indicated by the current bin of the current syntax element.

Abstract: Processing circuitry decodes information of a coding block in a current picture from a bitstream. The information indicates a bi-prediction mode without weight signaling. Weights associated with the bi-prediction mode are not signaled in the bitstream. Further, the processing circuitry determines a first motion vector associated with a first reference picture and a second motion vector associated with a second reference picture, and determine a first reference template in the first reference picture based on a current template of the coding block and the first motion vector and a second reference template in the second reference picture based on the current template and the second motion vector. The processing circuitry also calculates a weight for use in the bi-prediction mode based on the first reference template, the second reference template and the current template, and reconstructs the coding block using the bi-prediction with the calculated weight.

Abstract: Aspects of the disclosure provide methods and apparatuses for neural network processing, such as in video processing. In some examples, an apparatus for neural network processing includes processing circuitry. The processing circuitry determines that an input for a convolution operation includes a first input channel that is piecewise constant. Then, the processing circuitry calculates a first intermediate output channel based on other channels of the input for the convolution operation; and then generates an output of the convolution operation based on a combination (e.g., a linear combination) of the first intermediate output channel and the first input channel.

Abstract: Processing circuitry decodes information of a coding block from a bitstream. The information indicates an intra prediction mode for the coding block, a selection of a separable primary transform from a plurality of separable primary transform candidates, and a selection of a scan pattern from a plurality of scan pattern candidates. The processing circuitry determines whether selectable secondary non-separable transform is not applied to the bitstream and selectable separable primary transform is applied to the bitstream. Accordingly, processing circuitry determines residuals of the coding block from the bitstream based on the selection of the scan pattern and the selection of the separable primary transform. The processing circuitry reconstructs the coding block based on a combination of the residuals with an intra prediction of the coding block. The intra prediction of the coding block is based on the intra prediction mode.

Abstract: A method, computer program, and computer system is provided for video encoding and decoding. A bitstream of data corresponding to an image having pre-determined multiple regions is received, and a number is determined from the bitstream corresponding to a number of filters in an adaptive loop filter associated with the image. A region index to filter an index lookup table is decoded. The filter coefficients of the filters in the adaptive loop filter are decoded. The image is decoded based on the decoded filter coefficients and the decoded region index to filter the index lookup table.

Abstract: Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that decodes prediction information of a current block that is a part of a current picture in a video bitstream. The prediction information indicates a reference block for the current block. The processing circuitry generates filter coefficients of a filter operation based on neighboring reconstructed samples of the current block and neighboring reconstructed samples of the reference block that are co-located with the neighboring reconstructed samples of the current block. The filter operation compensates local changes to the current picture, such as illumination change or motion blur. The processing circuitry determines a prediction block for the current block based on the filter operation being performed on the reference block of the current block.

Abstract: According to an embodiment, a method of selecting a Rice parameter for encoding a video bitstream using at least one processor includes obtaining an absolute level corresponding to a current transform block; determining whether transform skip is enabled; generating a lookup variable based on the absolute level and the determination of whether the transform skip is enabled; obtaining the Rice parameter from a lookup table based on the lookup variable; and encoding a residual subblock based on the Rice parameter.

Abstract: An apparatus of video decoding can include circuitry configured to receive a lossless mode flag associated with a current block indicating whether a lossless coding mode is applied to the current block, determine that a lossy coding mode is not applied to the current block when the lossless mode flag indicates that the lossless coding mode is applied to the current block, and reconstruct the current block with the lossy coding mode disabled.

Abstract: A method of video decoding performed in a video decoder is disclosed. A first syntax element indicating whether a video is monochrome or includes color components that are encoded separately is generated. A second syntax element that indicates whether joint coding of chroma residuals is enabled based on whether the video is monochrome or includes color components that are encoded separately is generated. Further, a coded video bitstream that includes the first syntax element is generated. The coded video bitstream includes the second syntax element based on whether the video is monochrome or includes color components that are encoded separately. The first syntax element and the second syntax element are different syntax elements.

Abstract: A method of decoding an encoded video. The method includes obtaining the encoded video bitstream and determining whether a chroma array type of a video sequence included in the encoded video bitstream is a first chroma array type indicating that the video sequence includes multiple color planes and that the multiple color planes are jointly. In addition, based on determining that the chroma array type is not the first chroma array type, the method further includes setting a value of at least one syntax element to zero without parsing the at least one syntax element from the encoded video bitstream, and based on the value of the at least one syntax element being zero, decoding the video sequence without applying at least one tool corresponding to the at least one syntax element.

Abstract: A method, computer program, and computer system is provided for video coding. Video data comprising sub-blocks corresponding to neighborhood data is received. AC projections are computed based on at least a portion of the neighborhood data, and AC projections in the same direction are aggregated. One or more AC energy indices and one or more directionality indices are computed based on the aggregated AC projections. A class index is computed based on the computed AC energy and directionality indices. The video data is decoded based on the computed class index.

Abstract: A video encoding method includes obtaining a video bitstream; encoding the video bitstream based on a residual coding scheme and signaling information; and outputting the encoded video bitstream. Encoding the video bitstream includes: obtaining residual information associated with the video bitstream, wherein the residual information includes at least a remainder; obtaining a transform coefficient based on a current state, a Rice parameter, and a next state; and encoding the residual information based on the transform coefficient.

Abstract: Aspects of the disclosure provide methods and apparatuses for video processing. In some examples, an apparatus for video processing includes processing circuitry. The processing circuitry converts a picture in a subsampled format in a color space into a non subsampled format in the color space. Then, the processing circuitry clips values of a color component of the picture in the non subsampled format before providing the picture in the non subsampled format as an input to a neural network based filter.

Abstract: A versatile video coning method is provided for an electronic device. The method includes obtaining a video signal; partitioning the video signal into a plurality of coding blocks; generating a residual coding block from each coding block with or without transformation and quantization; splitting the residual coding block into a plurality of sub-blocks and each sub-block into a plurality of pixels; entropy coding a residual symbol level at each pixel in the residual coding block; and outputting a bitstream including entropy coded residual symbol levels. Entropy coding the residual symbol level at each pixel in the residual coding block includes context modeling of the residual symbol level of the pixel in a transform skip mode based on context information of at least three neighboring pixels of the pixel including a first pixel on the left, a second pixel on the above, and a third pixel on the left-above diagonal.

Abstract: According to an embodiment, a method of selecting a Rice parameter for encoding a video bitstream using at least one processor includes obtaining an absolute level corresponding to a current transform block; determining whether transform skip is enabled; generating a lookup variable based on the absolute level and the determination of whether the transform skip is enabled; obtaining the Rice parameter from a lookup table based on the lookup variable; and encoding a residual subblock based on the Rice parameter.

Abstract: A method of video decoding performed in a video decoder is disclosed. A syntax element can be received from a bitstream of a coded video that indicates whether a sequence of pictures are monochrome or include three color components that are coded separately. By inferring a value of a syntax element, a coding tool can be disabled when the syntax element indicates that the sequence of pictures are monochrome or include three color components that are coded separately. The coding tool uses multiple color components of a picture as input or depends on a chroma component of a picture. Examples of the disabled coding tools can include joint coding of chroma residuals, active color transform (ACT), or block-based delta pulse code modulation (BDPCM) for chroma component.

Abstract: Aspects of the disclosure provide methods and apparatuses for video processing. In some examples, an apparatus for video processing includes processing circuitry. The processing circuitry determines gating weights associated with expert modules based at least partially on a quantization parameter (QP) value. The expert modules are configured to process an input block that includes an image block being reconstructed based on the QP value. The processing circuitry then weights the expert modules based on the gating weights to generate an output image block corresponding to the image block.

Abstract: Aspects of the disclosure provide methods and apparatuses for neural network processing, such as in video processing. In some examples, an apparatus for neural network processing includes processing circuitry. The processing circuitry determines that an input for a convolution operation includes a first input channel that is piecewise constant. Then, the processing circuitry calculates a first intermediate output channel based on other channels of the input for the convolution operation; and then generates an output of the convolution operation based on a combination (e.g., a linear combination) of the first intermediate output channel and the first input channel.

Abstract: A method of decoding an encoded video. The method includes obtaining the encoded video bitstream and determining whether a chroma array type of a video sequence included in the encoded video bitstream is a first chroma array type indicating that the video sequence includes multiple color planes and that the multiple color planes are jointly. In addition, based on determining that the chroma array type is not the first chroma array type, the method further includes setting a value of at least one syntax element to zero without parsing the at least one syntax element from the encoded video bitstream, and based on the value of the at least one syntax element being zero, decoding the video sequence without applying at least one tool corresponding to the at least one syntax element.