Processing methods for motion compensation, an encoder, and a decoder are provided. The method includes the following. Determine a search position constellation with a point pointed by an initial motion vector as a center point, where the search position constellation includes N directions, search for at least one search point by using at least one type of step lengths in the directions, where the at least one search point at least includes at least one search point in diagonal directions. Search for at least one search position from the search position constellation based on a preset range coverage rule, where the preset range coverage rule is to arrange search points in the directions for search. Obtain a new motion vector according to the at least one search position, and perform motion compensation based on the new motion vector to obtain a prediction value of a coding unit (CU).

Processing methods for motion compensation, an encoder, and a decoder are provided. The method includes the following. Determine a search position constellation with a point pointed by an initial motion vector as a center point, where the search position constellation includes N directions, search for at least one search point by using at least one type of step lengths in the directions, where the at least one search point at least includes at least one search point in diagonal directions. Search for at least one search position from the search position constellation based on a preset range coverage rule, where the preset range coverage rule is to arrange search points in the directions for search. Obtain a new motion vector according to the at least one search position, and perform motion compensation based on the new motion vector to obtain a prediction value of a coding unit (CU).

There is provided a method of decoding an image, the method comprising: decoding information for motion information prediction of a current block from a bitstream, predicting motion information of the current block based on the information, refining motion information of the current block by using the decoded information and the predicted motion information of the current block and reconstructing the current block based on the refined motion information of the current block.

There is provided a method of decoding an image, the method comprising: decoding information for motion information prediction of a current block from a bitstream, predicting motion information of the current block based on the information, refining motion information of the current block by using the decoded information and the predicted motion information of the current block and reconstructing the current block based on the refined motion information of the current block.

Systems and methods for reducing latency through motion estimation and compensation techniques are disclosed. The systems and methods include a client device that uses transmitted lookup tables from a remote server to match user input to motion vectors, and tag and sum those motion vectors. When a remote server transmits encoded video frames to the client, the client decodes those video frames and applies the summed motion vectors to the decoded frames to estimate motion in those frames. In certain embodiments, the systems and methods generate motion vectors at a server based on predetermined criteria and transmit the generated motion vectors and one or more invalidators to a client, which caches those motion vectors and invalidators. The server instructs the client to receive input from a user, and use that input to match to cached motion vectors or invalidators. Based on that comparison, the client then applies the matched motion vectors or invalidators to effect motion compensation in a graphic interface. In other embodiments, the systems and methods cache repetitive motion vectors at a server, which transmits a previously generated motion vector library to a client. The client stores the motion vector library, and monitors for user input data. The server instructs the client to calculate a motion estimate from the input data and instructs the client to update the stored motion vector library based on the input data, so that the client applies the stored motion vector library to initiate motion in a graphic interface prior to receiving actual motion vector data from the server. In this manner, latency in video data streams is reduced.

Systems and methods for reducing latency through motion estimation and compensation techniques are disclosed. The systems and methods include a client device that uses transmitted lookup tables from a remote server to match user input to motion vectors, and tag and sum those motion vectors. When a remote server transmits encoded video frames to the client, the client decodes those video frames and applies the summed motion vectors to the decoded frames to estimate motion in those frames. In certain embodiments, the systems and methods generate motion vectors at a server based on predetermined criteria and transmit the generated motion vectors and one or more invalidators to a client, which caches those motion vectors and invalidators. The server instructs the client to receive input from a user, and use that input to match to cached motion vectors or invalidators. Based on that comparison, the client then applies the matched motion vectors or invalidators to effect motion compensation in a graphic interface. In other embodiments, the systems and methods cache repetitive motion vectors at a server, which transmits a previously generated motion vector library to a client. The client stores the motion vector library, and monitors for user input data. The server instructs the client to calculate a motion estimate from the input data and instructs the client to update the stored motion vector library based on the input data, so that the client applies the stored motion vector library to initiate motion in a graphic interface prior to receiving actual motion vector data from the server. In this manner, latency in video data streams is reduced.

A picture decoding method performed by a decoding apparatus according to the present disclosure includes obtaining motion prediction information from bitstream, generating an affine MVP candidate list including affine MVP candidates for a current block, deriving CPMVPs for respective CPs of the current block based on one of the affine MVP candidates included in the affine MVP candidate list, deriving the CPMVDs for the CPs of the current block based on information on CPMVDs for each of the CPs included in the obtained motion prediction information, deriving CPMVs for the CPs of the current block based on the CPMVPs and the CPMVDs, deriving prediction samples for the current block based on the CPMVs, and generating reconstructed samples for the current block based on the derived prediction samples.

There is provided an image processing apparatus and method that make it possible to suppress degradation of the encoding efficiency. In the case where primary transform that is a transform process for a prediction residual that is a difference between an image and a prediction image of the image is to be skipped, also secondary transform, which is a transform process for a primary transform coefficient obtained by the primary transform of the prediction residual, is skipped. The present disclosure can be applied, for example, to an image processing apparatus, an image encoding apparatus, an image decoding apparatus and so forth.

There is provided an image processing apparatus and method that make it possible to suppress degradation of the encoding efficiency. In the case where primary transform that is a transform process for a prediction residual that is a difference between an image and a prediction image of the image is to be skipped, also secondary transform, which is a transform process for a primary transform coefficient obtained by the primary transform of the prediction residual, is skipped. The present disclosure can be applied, for example, to an image processing apparatus, an image encoding apparatus, an image decoding apparatus and so forth.

Certain aspects of the present disclosure provide techniques for generating context-aware inferences using a machine learning model. The method generally includes receiving a time-series data sequence and a contextual model specifying characteristics of how objects behave in an environment in which the time-series data sequence was captured. A feature data set from the contextual model is extracted using a first machine learning model. Generally, the extracted feature data set comprises a representation of the specified characteristics of how objects behave in the environment. A future state of an object in the environment is predicted using the time-series data sequence and the extracted feature data set representing the specified characteristics of how objects behave in the environment as input into a second machine learning model. One or more actions are taken based on the predicted future state of the object in the environment.