A video decoder and method for supporting a prediction mode for predicting blocks of a video is configured to predict each of the blocks by extrapolating a neighborhood of the respective block into the block along a direction which varies across the respective block.

A decoder may determine reference signals of a chroma block. The decoder may decode a decision rule in a bitstream. The decoder may determine a chroma prediction model among one or more linear models and one or more non-linear models based on the decision rule. The decoder may generate a prediction of the chroma block based on the reference signals of the chroma block and the chroma prediction model. The decoder may determine a reconstruction of the chroma block based on the prediction of the chroma block and a decoded residual of the chroma block.

A decoder may determine reference signals of a chroma block. The decoder may decode a decision rule in a bitstream. The decoder may determine a chroma prediction model among one or more linear models and one or more non-linear models based on the decision rule. The decoder may generate a prediction of the chroma block based on the reference signals of the chroma block and the chroma prediction model. The decoder may determine a reconstruction of the chroma block based on the prediction of the chroma block and a decoded residual of the chroma block.

A method of decoding an image based on cross-channel prediction using artificial intelligence (AI) includes obtaining cross-channel prediction information by applying feature data for cross-channel prediction to a neural-network-based cross-channel decoder, obtaining a predicted image of a chroma image by performing cross-channel prediction based on a reconstructed luma image and the cross-channel prediction information, obtaining a residual image of the chroma image by applying feature data of the chroma image to a neural-network-based chroma residual decoder, and reconstructing the chroma image based on the predicted image and the residual image.

Disclosed is a video signal processing method comprising the steps of: acquiring a merge index which indicates a candidate for prediction of a current block among a plurality of candidates for the prediction of the current block, which are included in a merge candidate list; acquiring motion information of the current block on the basis of motion information corresponding to the candidate indicated by the merge index; when the motion information of the current block includes a plurality of motion vectors corresponding to a list of different reference pictures, comparing picture order count (POC) differences between each of the reference pictures corresponding to the plurality of motion vectors and the current picture including the current block; correcting the plurality of motion vectors on the basis of a result of the comparison; and reconstructing the current block on the basis of the plurality of corrected motion vectors.

Disclosed is a video signal processing method comprising the steps of: acquiring a merge index which indicates a candidate for prediction of a current block among a plurality of candidates for the prediction of the current block, which are included in a merge candidate list; acquiring motion information of the current block on the basis of motion information corresponding to the candidate indicated by the merge index; when the motion information of the current block includes a plurality of motion vectors corresponding to a list of different reference pictures, comparing picture order count (POC) differences between each of the reference pictures corresponding to the plurality of motion vectors and the current picture including the current block; correcting the plurality of motion vectors on the basis of a result of the comparison; and reconstructing the current block on the basis of the plurality of corrected motion vectors.

A video coding mechanism for viewpoint dependent video coding is disclosed. The mechanism includes mapping a spherical video sequence into a plurality of sub-picture video sequences. The mechanism further includes encoding the plurality of sub-picture video sequences as sub-picture bitstreams to support merging of the plurality of sub-picture bitstreams, the encoding ensuring that each sub-picture bitstream is self-referenced and two or more of the sub-picture bitstreams can be merged to generate a single video bitstream using a lightweight bitstream rewriting process that does not involve changing of any block-level coding results. A mergable indication is encoded to indicate that the sub-picture bitstream containing the indication is compatible with a multi-bitstream merge function for reconstruction of the spherical video sequence. A set of the sub-picture bitstreams and the mergable indication are transmitted toward the decoder to support decoding and displaying a virtual reality video viewport.

A video coding mechanism for viewpoint dependent video coding is disclosed. The mechanism includes mapping a spherical video sequence into a plurality of sub-picture video sequences. The mechanism further includes encoding the plurality of sub-picture video sequences as sub-picture bitstreams to support merging of the plurality of sub-picture bitstreams, the encoding ensuring that each sub-picture bitstream is self-referenced and two or more of the sub-picture bitstreams can be merged to generate a single video bitstream using a lightweight bitstream rewriting process that does not involve changing of any block-level coding results. A mergable indication is encoded to indicate that the sub-picture bitstream containing the indication is compatible with a multi-bitstream merge function for reconstruction of the spherical video sequence. A set of the sub-picture bitstreams and the mergable indication are transmitted toward the decoder to support decoding and displaying a virtual reality video viewport.

A method of video processing is provided to include: deciding a coding mode used for representing a current video block of a video in a coded representation of the video; and coding the current video block into the coded representation according to the coding mode, wherein use of alternative half-pel accuracy filters in addition to a default half-pel accuracy filter for representing motion information is disabled for the current video block due to use of the coding mode.

A method of video processing is provided to include: deciding a coding mode used for representing a current video block of a video in a coded representation of the video; and coding the current video block into the coded representation according to the coding mode, wherein use of alternative half-pel accuracy filters in addition to a default half-pel accuracy filter for representing motion information is disabled for the current video block due to use of the coding mode.