Abstract: An apparatus for video coding is provided. The apparatus includes processing circuitry that buffers first boundary pixel values of first reconstructed samples at a first node along a loop filter chain. The first node is associated with a non linear mapping based filter that is applied in the loop filter chain before a loop restoration filter. The first boundary pixel values are values of pixels at a frame boundary. The processing circuitry applies the loop restoration filter on to-be filtered reconstructed samples based on the buffered first boundary pixel values.

Abstract: Techniques are disclosed for improved video coding with virtual reference frames. A motion vector for prediction of a pixel block from a reference may be constrained based on the reference. In as aspect, if the reference is a temporally interpolated virtual reference frame with corresponding time close to the time of the current pixel block, the motion vector for prediction may be constrained magnitude and/or precision. In another aspect, a bitstream syntax for encoding the constrained motion vector may also be constrained. In this manner, the techniques proposed herein contribute to improved coding efficiencies.

Abstract: An image processing method includes obtaining statistics information of a block of an image frame, determining whether the statistics information satisfies a condition, and disabling cross-component filtering (CCF) for the block in response to the statistics information satisfying the condition.

Abstract: Disclosed is a method that includes receiving an image frame having a plurality of coded blocks, determining a prediction unit (PU) from the plurality of coded blocks, determining one or more motion compensation units arranged in an array within the PU, and applying a filter to one or more boundaries of the one or more motion compensation units. Also disclosed is a method that includes receiving a reference frame that includes a reference block, determining a timing for deblocking a current block, performing motion compensation on the reference frame to obtain a predicted frame that includes a predicted block, performing reconstruction on the predicted frame to obtain a reconstructed frame that includes a reconstructed PU, and applying, at the timing for deblocking the current block, a deblocking filter based on one or more parameters to the reference block, the predicted block, or the reconstructed PU.

Abstract: A method for video encoding includes determining a filter shape of a cross-component filter applied to a chroma coding block (CB), generating a first intermediate CB by applying a loop filter to the chroma CB, and generating a second intermediate CB by applying, to a corresponding luma CB, the cross-component filter applied to the chroma CB and having the determined filter shape. The method further includes determining a filtered chroma CB based on the first intermediate CB and the second intermediate CB by combining the loop filtered chroma CB with the cross-component filtered luma CB, and generating coded information of the chroma CB in a coded video bitstream. Determining the filter shape includes determining the filter shape of the cross-component filter based on the number of the filter coefficients and based on at least one of (i) the chroma subsampling format or (ii) the chroma sample type.

Abstract: A flexible coefficient coding (FCC) approach is presented. In the first aspect, spatial sub-regions are defined over a transform unit (TU) or a prediction unit (PU). These sub-regions organize the coefficient samples residing inside a TU or a PU into variable coefficient groups (VCGs). Each VCG corresponds to a sub-region inside a larger TU or PU. The shape of VCGs or the boundaries between different VCGs may be irregular, determined based on the relative distance of coefficient samples with respect to each other. Alternatively, the VCG regions may be defined according to scan ordering within a TU. Each VCG can encode a 1) different number of symbols for a given syntax element, or a 2) different number of syntax elements within the same TU or PU. Whether to code more symbols or more syntax elements may depend on the type of arithmetic coding engine used in a particular coding specification. For multi-symbol arithmetic coding (MS-AC), a VCG may encode a different number of symbols for a syntax element.

Abstract: Video coders and decoders perform transform coding and decoding on blocks of video content according to an adaptively selected transform type. The transform types are organized into a hierarchy of transform sets where each transform set includes a respective number of transforms and each higher-level transform set includes the transforms of each lower-level transform set within the hierarchy. The video coders and video decoders may exchange signaling that establishes a transform set context from which a transform set that was selected for coding given block(s) may be identified. The video coders and video decoders may exchange signaling that establishes a transform decoding context from which a transform that was selected from the identified transform set to be used for decoding the transform unit. The block(s) may be coded and decoded by the selected transform.

Abstract: Techniques are described for express and implied signaling of transform mode selections in video coding. Information derived from coefficient samples in a given transform unit (TU) or prediction unit (PU) may constrain or modify signaling of certain syntax elements at the coding block (CB), TU, or PU levels. For instance, based on the spatial locations of decoded coefficients, the spatial patterns of coefficients, or the correlation with the coefficients in neighboring blocks, various syntax elements such as the transform type and related flags/indices or secondary transform modes/flags indices, a residual coding mode, intra and inter prediction modes, and scanning order may be disabled or constrained. In another case, if the coefficient samples match a desired spatial pattern or have other desired properties then a default transform type, a default secondary transform type, a default intra and inter prediction mode or other block level modes may be inferred at the decoder side.

Abstract: A method for video coding, executable by a processor, includes receiving video data, determining a directionality of a sample block of the received video data, the directionality corresponding to a descriptor, applying a geometric transformation in which filter coefficients of a cross-component filter or reconstructed samples in a filter support region are rotated by a first amount based on the directionality being a first direction and rotated by a second amount based on the directionality being a second direction different from the first direction, and decoding the video data based on the applied geometric transformation.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data having a coding tree unit size is received. The coding tree unit size associated with the video data is signaled by setting two or more flags. The video data is encoded/decoded based on the flags corresponding to the signaled coding tree unit size.

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: In a method for filtering in video decoding, a coded video bitstream that includes filter shape index information is received. A filter shape configuration of a video filter is determined based on the filter shape index information. The filter shape index information indicates that a number of filter taps of the filter shape configuration is less than five. Offset values associated with the filter shape configuration of the video filter are determined. The video filter is applied on a sample based on the offset values associated with the filter shape configuration.

Abstract: Systems and methods may provide flexible picture partitioning, a method includes receiving a bitstream, that includes a picture, the picture partitioned into a plurality of coding tree units (CTUs), wherein at least one row or column of CTUs, among the plurality of CTUs of the picture, that is adjacent to a boundary of the picture has a size dimension that is smaller than a corresponding size dimension of each CTU among the plurality of CTUs that is not adjacent to any boundary of the picture; and encoding the bitstream based on the plurality of CTUs, wherein the at least one row or column of CTUs includes a first CTU row or a first CTU column of the picture that is adjacent to a top boundary or left boundary of the picture, respectively.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus includes processing circuitry. For example, the processing circuitry obtains reconstructed samples in a temporal source frame that is different from a current frame, and determines filter coefficients of a filter for a current block in the current frame based on at least the reconstructed samples in the temporal source frame. The processing circuitry generates prediction information of the current block based on the determined filter coefficients. The temporal source frame is an inter coded frame that satisfies at least one of a quantization parameter (QP) requirement, a temporal distance requirement, and a reference picture requirement.

Abstract: A method for in-loop sample offset filtering in a video decoder is disclosed. The method includes extracting at least one loop filtering parameter from a coded video bitstream for a reconstructed sample of a first color component in a current picture reconstructed from the coded video bitstream, the at least one loop filtering parameter comprising a flag, and determining based on the flag a type of sample offset filter to be applied to the reconstructed sample of the first color component, the type of sample offset filter being either a predefined sample offset filter type or an encoder-derived sample offset filter type.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry. For example, the processing circuitry generates first reconstructed samples of a block, and applies a filter to multiple color components of the first reconstructed samples of the block to determine offsets to be applied to one or more color components. Then, the processing circuitry generates second reconstructed samples of the block based on the offsets for the one or more color components and the first reconstructed samples of the block.

Abstract: A method for filtering includes determining, by a processor, a first offset value by applying a non linear mapping based filter to first reconstructed samples at a first node along a loop filter chain that includes a plurality of video filters. The method further includes applying, by the processor, the first offset value to an intermediate reconstructed sample at a second node along the loop filter chain to generate a second reconstructed sample, wherein the second node is one of an input node of the loop filter chain or an output node of the loop filter chain.

Abstract: A method, computer program, and computer system is provided for video coding. Video data comprising a chroma component and a luma component is received. Luma samples are extracted from the luma component of the received video data. The chroma component is filtered based on the extracted luma samples using a cross-component adaptive loop filter (CC-ALF). Coefficients associated with the CC-ALF are constrained to be less than a sum of a bit-depth value associated with the luma samples and a positive offset value.

Abstract: Systems and methods may provide flexible picture partitioning, a method includes receiving a bitstream, that includes a picture, the picture partitioned into a plurality of coding tree units (CTUs), wherein at least one row or column of CTUs, among the plurality of CTUs of the picture, that is adjacent to a boundary of the picture has a size dimension that is smaller than a corresponding size dimension of each CTU among the plurality of CTUs that is not adjacent to any boundary of the picture; and encoding the bitstream based on the plurality of CTUs, wherein the at least one row or column of CTUs includes a first CTU row or a first CTU column of the picture that is adjacent to a top boundary or left boundary of the picture, respectively.

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 based on at least the identified reference samples. The video data is encoded/decoded based on the predicted sign values.