Abstract: Methods of enabling and disabling a decoder-side motion vector refinement (DMVR) video decoder and/or encoder are described. One example method includes determining a width (W) and a height (H) of a video block, making a determination, based on a condition of the video block, between enabling and disabling a decoder side motion vector refinement step for a conversion between the video block and a coded representation of the video block, in a case that the determination is enabling, performing the conversion by enabling the decoder side motion vector refinement step; and in a case that the determination is disabling, performing the conversion by disabling the decoder side motion vector refinement step, wherein the decoder side motion vector refinement step includes refining value of a motion vector signaled in the coded representation and using the refined value during the conversion.

Abstract: An image encoding/decoding method and apparatus are provided. An image decoding method performed by an image decoding apparatus may include determining a prediction mode of a current block, generating a prediction block of the current block based on intra block copy (IBC) prediction mode information, based on the prediction mode of the current block being an IBC prediction mode, determining a size of a transform block of the current block based on a color component of the current block, generating a residual block of the current block based on the size of the transform block; and reconstructing the current block based on the prediction block and the residual block of the current block.

Abstract: The present invention relates to an image encoding/decoding method and apparatus. The image decoding method according to the present invention may comprise constructing N MPM lists for a current block, wherein N is equal to or greater than 1, deriving an intra prediction mode of the current block based on the N MPM lists, and performing intra prediction for the current block based on the intra prediction mode.

Abstract: A motion vector prediction method includes parsing a bitstream to obtain an index value of a candidate motion vector list and constructing the candidate motion vector list that includes. candidate motion vectors of K control points of a current block. The candidate motion vectors of K control points are obtained based on a 2N-parameter affine transform model used for a neighboring block of the current block, where N and K are integers greater than or equal to 2 and less than or equal to 4 with N not being equal to K. The method further includes determining, in the candidate motion vector list, target candidate motion vectors of the K control points based on the index value and obtaining a predicted motion vector of each subblock of the current block based on the target candidate motion vectors of the K control points.

Abstract: According to embodiments according to the present document, merge mode motion vector differences (MMVD) and symmetric motion vector differences (SMVD) may be performed on the basis of reference picture types and, in particular, short-term reference pictures may be used. Accordingly, prediction performance and coding efficiency in an inter prediction mode may be increased.

Abstract: An encoding device encodes each encoding-target block.

Abstract: A method of coding video data, the method comprising: reconstructing a block of the video data; and applying a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.

Abstract: Video encoding or decoding methods and apparatuses receive input video data of a luma block and one or more corresponding chroma blocks, compare sizes of the luma and chroma blocks with a maximum transform skip size, and signal or parse a BDPCM luma enabling flag for the luma block when the size of the luma block is smaller than or equal to the maximum transform skip size, and signal or parse a BDPCM chroma enabling flag for the chroma block when the size of the chroma block is smaller than or equal to the maximum transform skip size. The size of the chroma block is derived from the size of the luma block and a color format sampling structure. The luma block is encoded/decoded by BDPCM based on the BDPCM luma enabling flag and the chroma block is encoded/decoded by BDPCM according to the BDPCM chroma enabling flag.

Abstract: Provided is a video decoding method including: obtaining, from a sequence parameter set, sequence merge mode with motion vector difference (sequence MMVD) information indicating whether an MMVD mode is applicable in a current sequence; when the MMVD mode is applicable according to the sequence MMVD information, obtaining, from a bitstream, first MMVD information indicating whether the MMVD mode is applied in a first inter prediction mode for a current block included in the current sequence; when the MMVD mode is applicable in the first inter prediction mode according to the first MMVD information, reconstructing a motion vector of the current block which is to be used in the first inter prediction mode, by using a distance of a motion vector difference and a direction of a motion vector difference obtained from the bitstream; and reconstructing the current block by using the motion vector of the current block.

Abstract: A method for video processing includes performing a conversion between a current video block and a bitstream representation of the current video block using an inter-prediction coding scheme based on an n-order polynomial model using a first variable associated with the current video block, where n is an integer greater than or equal to zero, wherein the conversion includes generating the current video block from the bitstream representation or generating the bitstream representation from the current video block; and performing illumination compensation for the current video block using the n-order polynomial model during the conversion.

Abstract: Efficient prediction of samples within a block in a video encoder and decoder by means of computing both an inter-predicted prediction hypothesis as well as an intra-predicted prediction-hypothesis. The two prediction hypotheses are then combined together by means of parametric transformation to form a new prediction hypothesis which may be more accurate in predicting the content of the original block.

Abstract: A camera system includes: a first camera and a second camera; a camera adaptor box; and a camera control unit.

Abstract: Provided is an encoder that achieves further improvement. The encoder includes processing circuitry and memory. Using the memory, the processing circuitry: obtains two prediction images from two reference pictures; derives a luminance gradient value of each pixel position in each of the two prediction images; derives a luminance local motion estimation value of each pixel position in a current block; generates a luminance final prediction image using a luminance value and the luminance gradient value in each of the two prediction images, and the luminance local motion estimation value of the current block; and generates a chrominance final prediction image using at least one of the luminance gradient value of each of the two prediction images or the luminance local motion estimation value of the current block, and chrominance of each of the two prediction images.

Abstract: A video signal processor is configured to: obtain at least one transform block for a residual signal of a current block from a video signal bitstream, wherein the transform block comprises a plurality of transform coefficients two-dimensionally arranged, determine, on the basis of length information of a first side of the transform block, a horizontal transform kernel for horizontal transformation of the transform block, regardless of a length of a second side of the transform block, which is orthogonal to the first side, determine, on the basis of length information of the second side, a vertical transform kernel for vertical transformation of the transform block, regardless of a length of the first side, obtain the residual signal of the current block by performing, on the transform block, inverse transformation using the horizontal transform kernel and the vertical transform kernel, and reconstruct the current block based on the residual signal.

Abstract: An image decoding method according to the present document comprises a step for deriving a modified transform coefficient, wherein the step for deriving the modified transform coefficient comprises a step for determining whether or not to parse an LFNST index on the basis of whether or not the width and height of a current block satisfy a condition about whether the LFNST can be applied, and whether or not the condition about whether the LFNST can be applied is satisfied is determined on the basis of a tree type and a color format of the current block and whether or not an ISP is applied to the current block.

Abstract: The present invention relates to a block partitioning structure in video coding technology, and a video encoding and decoding method and apparatus using the same, wherein the video encoding and decoding method includes the steps of acquiring quad-partitioning information of a block; acquiring bi-partitioning information of the block when the acquired quad-partitioning information of the block does not indicate four partitions; acquiring partitioning direction information for bi-partitioning of the block when the acquired bi-partitioning information of the block indicates two partitions; acquiring information on whether to perform any other type of partitioning, when the acquired bi-partitioning information of the block does not indicate two partitions; and acquiring additional information required for the any other type of partitioning, when the acquired information on whether to perform any other type of partitioning indicates that the any other type of partitioning is performed.

Abstract: Embodiments of the present invention provide a method and apparatus for processing a video signal. A method for decoding an image signal according to an embodiment of the present invention comprises the steps of: for a current block having a width and a height different from each other, determining a modified intra prediction mode from an intra prediction mode, on the basis of a ratio between the width and the height of the current block and the intra prediction mode; determining an inverse non-separable transform set on the basis of the modified intra prediction mode; and applying an inverse non-separable transform matrix selected from the inverse non-separable transform set with respect to the top-left region of the current block, which is determined according to the width and the height of the current block.

Abstract: The present disclosure provides methods and devices of construct a candidate merge list for Intra block copy (IBC) mode, the method comprising: inserting a block vector of a left neighboring block of a current block into an initial merge list, when the left neighboring block is available and the left neighboring block is using IBC mode; inserting a block vector of an above neighboring block of the current block into the initial merge list, when the above neighboring block is available, the above neighboring block is using IBC mode and the block vector of the above neighboring block is not same as the block vector of the left neighboring block; inserting a block vector of the last candidate in a history based motion vector predictor (HMVP) into the initial merge list; obtaining a block vector of the current block according to the initial merge list.

Abstract: Embodiments of video coding systems and methods are described for reducing coding latency introduced by decoder-side motion vector refinement (DMVR). In one example, two non-refined motion vectors are identified for coding of a first block of samples (e.g. a first coding unit) using bi-prediction. One or both of the non-refined motion vectors are used to predict motion information for a second block of samples (e.g. a second coding unit). The two non-refined motion vectors are refined using DMVR, and the refined motion vectors are used to generate a prediction signal of the first block of samples. Such embodiments allow the second block of samples to be coded substantially in parallel with the first block without waiting for completion of DMVR on the first block. In additional embodiments, optical-flow-based techniques are described for motion vector refinement.

Abstract: A motion vector prediction method based on an affine motion model and a device are provided. The method includes: obtaining one spatial reference block of a to-be-processed picture block; determining a plurality of preset subblock locations of the spatial reference block; obtaining motion vectors corresponding to preset pixel locations of the to-be-processed picture block that are extrapolated from motion vectors corresponding to the preset subblock locations; and obtaining motion vectors corresponding to a plurality of subblock locations of the to-be-processed picture block that are interpolated from the motion vectors corresponding to the preset pixel locations. According to this application, prediction accuracy in coding can be improved, and coding efficiency can be improved.