Inter-frame coding unit size division method based on neural network

Abstract

The invention relates to the technical field of hardware encoders, in particular to an inter-frame coding unit size division method based on a neural network. The method comprises the following steps: acquiring a coding unit of a first preset size; inputting the coding unit into a trained neural network model to obtain a coding unit of a second preset size; finding a corresponding position in a model prediction result and carrying out addition and average operation to obtain a probability that the coding unit is not divided; calculating the probability of dividing the coding unit into sub-blocks, and then carrying out addition and average operation to backtrack to the size of the coding unit to obtain the probability of a coding unit with a second preset size in the current division mode; obtaining a preset number of probabilities, performing size comparison and sorting, and selecting the division modes corresponding to the first N maximum probabilities for division. According to the method, the complexity of the statistical information and manual feature design process is reduced, the data dependence degree is reduced, and the division mode is flexibly limited.

Description

technical field [0001] The present application relates to the technical field of inter-frame coding, and more specifically, the present application relates to a method for dividing the size of an inter-frame coding unit based on a neural network. Background technique [0002] AVS stands for China's digital audio and video codec technology standard, and AVS3 represents a new generation of codec technology standard. AVS3 uses inter-frame prediction technology and uses the feature of great similarity between adjacent images to effectively remove video time-domain redundancy. remaining purpose. In the state-of-the-art coding block flag (CBF)-based early termination partitioning method, if there is zero CBF for all chrominance and luma components, the remaining partitioning modes of the current coding unit (CU) can be completely skipped. There is also a method to conditionally evaluate a specific set of inter-frame partition modes based on intermediate coding information, but bo...

AI Technical Summary

Problems solved by technology

There is also a method to conditionally evaluate a specific set of inter-frame partition modes based on intermediate coding information, but both have the disadvantage of being highly dependent on statistics and hand-designed features, and cannot fully display the statistics and coding of natural videos. Decoder Behavior

In short, the traditional encoder under the AVS3 standard processes a series of coding units through an iterative division method, and the division method is developing towards a diverse and flexible division structure, which significantly increases the division complexity and consumes serious computing resources.

Images