A Convolutional Neural Network Construction Method for Fractional Pixel Interpolation in Video Coding

Abstract

The present invention provides a method for constructing a convolutional neural network for video coding fractional pixel interpolation, comprising: collecting images of different contents and resolutions to form original training data sets containing data of different types and coding complexity; The training data set is preprocessed to obtain training data that conforms to the characteristics of video coding inter-frame prediction fractional pixel interpolation; a deep convolutional neural network is built to obtain a convolutional neural network structure suitable for video coding inter-frame prediction fractional pixel interpolation; The processed data is input into the built convolutional neural network, and the original training data set is used as the corresponding true value to train the built convolutional neural network. The invention ensures that the convolutional neural network can be trained smoothly, and the fractional pixels obtained by using the trained convolutional neural network interpolation meet the characteristic requirements of video encoding fractional pixel interpolation, and the fractional pixel interpolation using the invention can realize the improvement of video encoding efficiency.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a convolutional neural network method suitable for inter-frame prediction fractional pixel interpolation of video coding. Background technique [0002] Inter-frame prediction is a key technology in video coding standards. By using the similarity of video content between frames, the temporal redundancy of video can be effectively removed, thereby improving the coding and compression efficiency. At the same time, due to the discrete sampling operation in the digitization process, the real object motion does not necessarily follow the sampling grid. In order to further improve the accuracy of object motion prediction, in video coding standards, the motion of objects is in units of fractional pixels. The pixel values ​​at the fractional pixel positions on the sampling grid do not really exist. In the application, the pixel values ​​at these fractional pixel posi...

AI Technical Summary

Problems solved by technology

In addition, for the inter-frame predicted fractional pixel interpolation, the pixels at the fractional position do not really exist. Therefore, during the training process of the convolutional neural network, there is no real truth value to refer to, resulting in the normal training.

Images