Provided are inter prediction methods and a decoder. In the method, a bitstream is parsed to determine a prediction mode parameter of a current block; a Geometrical Partition Mode (GPM) parameter of the current block and a merge candidate list of the current block and attribute information of motion information in the merge candidate list are determined when the prediction mode parameter indicates to determine an inter prediction value of the current block by using GPM; a first motion information mapping table of a first partition and a second motion information mapping table of a second partition are determined according to the GPM parameter, merge candidate list and attribute information; and the inter prediction value of the current block is determined based on the first and second motion information mapping tables and merge candidate list.

Provided are inter prediction methods and a decoder. In the method, a bitstream is parsed to determine a prediction mode parameter of a current block; a Geometrical Partition Mode (GPM) parameter of the current block and a merge candidate list of the current block and attribute information of motion information in the merge candidate list are determined when the prediction mode parameter indicates to determine an inter prediction value of the current block by using GPM; a first motion information mapping table of a first partition and a second motion information mapping table of a second partition are determined according to the GPM parameter, merge candidate list and attribute information; and the inter prediction value of the current block is determined based on the first and second motion information mapping tables and merge candidate list.

A device includes a memory and one or more processors. The memory is configured to store instructions. The one or more processors are configured to execute the instructions to apply a neural network to a first image to generate an enhanced image. The one or more processors are also configured to execute the instructions to adjust at least a portion of a high-frequency component of the enhanced image based on a motion compensation operation to generate an adjusted high-frequency image component. The one or more processors are further configured to execute the instructions to combine a low-frequency component of the enhanced image and the adjusted high-frequency image component to generate an adjusted enhanced image.

At least a method and an apparatus are provided for efficiently encoding or decoding video. For example, a plurality of different motion prediction modes are obtained for a current block. The current block is encoded or decoded based on a combination of the plurality of different motion prediction modes with corresponding weights, wherein the combination with the corresponding weights comprising at least two inter prediction modes, or an inter prediction mode and an intra prediction mode. Both triangle prediction and multi-hypothesis prediction are allowed to be indicated in one or more lists of possible motion vector candidates, such as, e.g., in advanced motion vector prediction (AMVP) mode.

At least a method and an apparatus are provided for efficiently encoding or decoding video. For example, a plurality of different motion prediction modes are obtained for a current block. The current block is encoded or decoded based on a combination of the plurality of different motion prediction modes with corresponding weights, wherein the combination with the corresponding weights comprising at least two inter prediction modes, or an inter prediction mode and an intra prediction mode. Both triangle prediction and multi-hypothesis prediction are allowed to be indicated in one or more lists of possible motion vector candidates, such as, e.g., in advanced motion vector prediction (AMVP) mode.

In an inter prediction encoding method, a picture is divided into a plurality of coding units. Motion estimation traversal is performed on motion vector predictions (MVPs) in a specified inter prediction mode to obtain candidate motion vectors. A motion vector set is determined from the MVPs and the candidate motion vectors. The motion vector set includes a target MVP from the MVPs and a target motion vector from the candidate motion vectors. Interpolation mode transversal and motion mode transversal are performed for each of the coding units based on the motion vector set to obtain a target interpolation mode and a target motion mode corresponding to the respective coding unit.

In an inter prediction encoding method, a picture is divided into a plurality of coding units. Motion estimation traversal is performed on motion vector predictions (MVPs) in a specified inter prediction mode to obtain candidate motion vectors. A motion vector set is determined from the MVPs and the candidate motion vectors. The motion vector set includes a target MVP from the MVPs and a target motion vector from the candidate motion vectors. Interpolation mode transversal and motion mode transversal are performed for each of the coding units based on the motion vector set to obtain a target interpolation mode and a target motion mode corresponding to the respective coding unit.

Motion vectors of a first reference frame are permitted to point to a plurality of further reference frames. A method of storing the motion vectors comprises, when a block of the first reference frame has two motion vectors (V2A, V2B) initially, selecting one of the two motion vectors, the non-selected motion vector not being stored. The selected motion vector may be scaled. This can reduce the motion vector memory size.

Motion vectors of a first reference frame are permitted to point to a plurality of further reference frames. A method of storing the motion vectors comprises, when a block of the first reference frame has two motion vectors (V2A, V2B) initially, selecting one of the two motion vectors, the non-selected motion vector not being stored. The selected motion vector may be scaled. This can reduce the motion vector memory size.

This application discloses a motion vector obtaining method and apparatus, a computer device, and a storage medium. In the method, an initial motion vector of a to-be-processed picture block is determined by using a location relationship between a reference block and the to-be-processed picture block. When the reference block and the to-be-processed picture block are located in a same coding tree block, a decoder uses an initial motion vector of the reference block as the initial motion vector of the to-be-processed picture block. When the reference block and the to-be-processed picture block are located in different coding tree blocks, the decoder uses a final motion vector of the reference block as the initial motion vector of the to-be-processed picture block.