Provide are an inter prediction method, encoder, decoder, and storage medium. Said method comprises: determining a prediction mode parameter of the current block; when the prediction mode parameter indicates a geometrical partitioning prediction mode is used for determining inter prediction of the current block, determining a geometrical partitioning prediction mode parameter of the current block; according to the geometrical partitioning prediction mode parameter, determining a first and a second prediction value and a weight index corresponding to the sample in the current block; clipping the weight index corresponding to the sample in the current block to obtain absolute information of the weight index; determining a first and a second weight value based on absolute information of the weight index; and determining an inter prediction of the sample of the current block according to weighted combination of the first prediction value, first weight value, second prediction value and second weight value.

A method, an apparatus and non-transitory computer-readable storage medium for video data process are provided. The method includes receiving a bitstream comprising a coding unit coded in a geometric partition mode (GPM); decoding a first parameter associated with the coding unit, the first parameter indicating whether template matching being applied to the coding unit; and determining, according to the first parameter, motion information for the coding unit, wherein when the first parameter indicates the template matching is applied to the coding unit, the motion information is refined using the template matching.

A macro block size determining unit 1 determines the size of each macro block on a frame-by-frame basis. A macro block dividing unit 2 divides an inputted image into macro blocks each having the size determined by the macro block size determining unit 1. A macro block coding unit 3 determines a coding mode for each of the macro blocks divided by the macro block dividing unit 2, and codes pixel values in each of the macro blocks in the determined coding mode.

A macro block size determining unit 1 determines the size of each macro block on a frame-by-frame basis. A macro block dividing unit 2 divides an inputted image into macro blocks each having the size determined by the macro block size determining unit 1. A macro block coding unit 3 determines a coding mode for each of the macro blocks divided by the macro block dividing unit 2, and codes pixel values in each of the macro blocks in the determined coding mode.

Provided is a video decoding method performed by a decoding apparatus, which includes: obtaining split information for a target block from a bitstream; splitting the target block into a first sub-block and a second sub-block based on a split boundary indicated by the split information; deriving a first motion information candidate list for the first sub-block and a second motion information candidate list for the second sub-block based on the split information for the target block; performing inter prediction of the first sub-block based on the first motion information candidate list; and performing inter prediction of the second sub-block based on the second motion information candidate list, in which the first sub-block and the second sub-block are non-rectangular blocks, and the first motion information candidate list for the first sub-block is different from the second motion information candidate list for the second sub-block.

Devices, systems and methods for sample refinement and filtering method for video coding are described. In an exemplary aspect, a method for video processing includes modifying, for a conversion between a block of a video and a bitstream representation of the video, a refinement value for a prediction sample in the block by applying a clipping operation to refinement value. The refinement value is derived based on a gradient value of an optical flow coding process. An output of the clipping operation is within a range. The method also includes refining the prediction sample based on the refinement value and performing the conversion based on the refined prediction sample.

Techniques related to providing motion estimation for arbitrary pixel block shapes are discussed. Such techniques may include generating a distortion mesh for a pixel block based on multiple calls to a motion estimation such that the distortion mesh includes distortion values associated with regions of the pixel block, a seed motion vector, and candidate motion vectors, and determining a best motion vector for the pixel block based on the distortion mesh.

Techniques related to providing motion estimation for arbitrary pixel block shapes are discussed. Such techniques may include generating a distortion mesh for a pixel block based on multiple calls to a motion estimation such that the distortion mesh includes distortion values associated with regions of the pixel block, a seed motion vector, and candidate motion vectors, and determining a best motion vector for the pixel block based on the distortion mesh.

For a bi-prediction block, the initial motion field can be refined using a DNN. In one implementation, the initial motion field is integer rounded to obtain initial prediction blocks. Based on the initial prediction, the DNN can generate motion refinement information, which is scaled and added to the sub-pel residual motion from the initial motion field to generate a refined motion field. The scaling factor can take a default value, or be based on the motion asymmetry. While the initial motion field is usually block based on sub-block based, the refined motion field is pixel based or sub-block based and can be at an arbitrary accuracy. The same refinement process is performed at both the encoder and decoder, and thus the motion refinement information need not to be signaled. Whether the refinement is enabled can be determined based on the initial motion, the block activities and the block size.

Techniques related to improved video coding based on face detection, region extraction, and tracking are discussed. Such techniques may include performing a facial search of a video frame to determine candidate face regions in the video frame, testing the candidate face regions based on skin tone information to determine valid and invalid face regions, rejecting invalid face regions, and encoding the video frame based on valid face regions to generate a coded bitstream.