A method of decoding a bitstream by an electronic device is provided. The electronic device receives the bitstream and determines an affine enabled flag corresponding to one or more image frames from the bitstream. The electronic device determines a maximum index corresponding to the one or more image frames from the bitstream when the affine enabled flag is true. An index value of the maximum index is in an index range of 0 to N−K, N being a first integer and K being a second integer less than N. The electronic device determines a maximum number of zero or more subblock-based merging motion vector prediction (MVP) candidates based on the maximum index when the affine enabled flag is true. The electronic device reconstructs the one or more image frames based on the maximum number of zero or more subblock-based merging MVP candidates.

Systems and methods are described for video coding using affine motion models with adaptive precision. In an example, a block of video is encoded in a bitstream using an affine motion model, where the affine motion model is characterized by at least two motion vectors. A precision is selected for each of the motion vectors, and the selected precisions are signaled in the bitstream. In some embodiments, the precisions are signaled by including in the bitstream information that identifies one of a plurality of elements in a selected predetermined precision set. The identified element indicates the precision of each of the motion vectors that characterize the affine motion model. In some embodiments, the precision set to be used is signaled expressly in the bitstream; in other embodiments, the precision set may be inferred, e.g., from the block size, block shape or temporal layer.

A video coder may determine a motion vector of a non-adjacent block of a current picture of the video data. The non-adjacent block is non-adjacent to a current block of the current picture. Furthermore, the video coder determines, based on the motion vector of the non-adjacent block, a motion vector predictor (MVP) for the current block. The video coder may determine a motion vector of the current block. The video coder may also determine a predictive block based on the motion vector of the current block.

A video coder may determine a motion vector of a non-adjacent block of a current picture of the video data. The non-adjacent block is non-adjacent to a current block of the current picture. Furthermore, the video coder determines, based on the motion vector of the non-adjacent block, a motion vector predictor (MVP) for the current block. The video coder may determine a motion vector of the current block. The video coder may also determine a predictive block based on the motion vector of the current block.

A method of video coding at a video coding device includes performing a deformable convolution through a deformable convolutional deep neural network (DNN) to generate one or more first feature maps based on a set of one or more previously reconstructed reference frames, generating a predicted frame based on the one or more first feature maps, and reconstructing a current frame based on the predicted frame. In an embodiment, a set of one or more second feature maps corresponding to the one or more previously reconstructed reference frames can be generated based on a feature extraction DNN. One or more offset maps corresponding to the one or more second feature maps can be generated, respectively, using an offset generation DNN.

An image decoding method according to the present document includes obtaining motion prediction information for a current block from a bitstream, generating an affine MVP candidate list for the current block, deriving CPMVPs for CPs of the current block based on the affine MVP candidate list, deriving CPMVDs for the CPs of the current block based on the motion prediction information, deriving CPMVs for the CPs of the current block based on the CPMVPs and the CPMVDs, and deriving prediction samples for the current block based on the CPMVs.

Aspects of the disclosure provide a method and an apparatus for video decoding. The apparatus includes processing circuitry that decodes prediction information of a current block in a current picture. The prediction information indicates that an adaptive motion vector prediction (AMVP) mode is applied to the current block with an adaptive motion vector resolution (AMVR) mode. The prediction information indicates motion information. The processing circuitry determines a respective first motion vector predictor (MVP) for each of a first plurality of motion vector resolutions (MVRs) corresponding to a first reference picture based on the motion information and the respective first MVR in the first plurality of MVRs. The processing circuitry perform template matching (TM) by determining TM costs based at least on the first plurality of MVRs and the first MVPs. The processing circuitry generates an adaptive order of the first plurality of MVRs based on the TM costs.

An apparatus is provided and includes processing circuitry that determines a plurality of first sub-block motion vectors for a plurality of sub-blocks of a current block. The processing circuitry determines a plurality of second sub-block motion vectors by respectively constraining the plurality of first sub-block motion vectors according to a first target range. The processing circuitry determines a set of gradient values associated with a current sample location in a current sub-block from the plurality of sub-blocks according to a reference sub-block. The processing circuitry determines a set of adjustment values associated with the current sample location according to the set of gradient values and an adjustment vector associated with the current sample location. Further, the processing circuitry generates a predicted sample associated with the current sample location according to a combination of a corresponding sample in the reference sub-block and the set of adjustment values.

A method and apparatus for video encoding/decoding are provided. In some examples, an apparatus includes processing circuitry for video decoding. The processing circuitry decodes prediction information of a block in a current picture from a coded video bitstream. The prediction information is indicative of an affine model in an intra block copy mode. The processing circuitry determines parameters for the affine model that transforms between the block and a reference block in a region of the current picture that has been reconstructed. Then, the processing circuitry reconstructs at least a sample of the block based on the affine model.

A method and apparatus for video encoding/decoding are provided. In some examples, an apparatus includes processing circuitry for video decoding. The processing circuitry decodes prediction information of a block in a current picture from a coded video bitstream. The prediction information is indicative of an affine model in an intra block copy mode. The processing circuitry determines parameters for the affine model that transforms between the block and a reference block in a region of the current picture that has been reconstructed. Then, the processing circuitry reconstructs at least a sample of the block based on the affine model.