Video loop filter based on deep convolutional network

Abstract

The invention discloses a video loop filtering method based on a deep convolutional network. The method comprises the following steps: step 1, making a training data set for loop filtering network training; step 2, constructing a network model for video filtering; step 3, taking the training data set obtained in the step 1 as a training set of the network, respectively training two models for intra-frame prediction frame filtering and inter-frame prediction frame filtering, and forming a video filtering network model by the two models; training the video filtering network model by taking a minimized loss function as an optimization target; and step 4, integrating the video filtering network model trained in the step 3 into video encoding software to complete the whole video encoding process and obtain a reconstructed frame after passing through the video filtering network. Compared with a traditional filtering method, the method has the advantages that the image quality of the video reconstruction frame is improved, the accuracy of inter-frame prediction is improved, the coding efficiency is improved, the filtered image frame has higher reconstruction quality, and the video codingefficiency is greatly improved.

Description

technical field [0001] The invention belongs to the fields of computer vision and video coding, and in particular relates to a video loop filter based on a deep convolutional network. Background technique [0002] As the most advanced video coding standard, HEVC (High Efficiency Video Coding) has greatly improved the compression efficiency compared with previous video coding standards. Although HEVC's loop filter significantly improves the quality of reconstructed frames in video coding, HEVC's loop filter technology also has many limitations. For example, compressed video still suffers from unpleasant image artifacts caused by quantization. With the development of the Internet and new media, more and more videos are played and distributed every day. Therefore, there is an urgent need to provide videos with higher quality and smaller size. [0003] All existing coding standards adopt a hybrid coding framework, including processes such as intra / inter prediction, variation,...

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the limitations of existing video loop filters, and proposes a video loop filtering method based on deep convolutional network, using the network model obtained based on deep convolutional network learning to realize the difference between the distorted image and the original image. More accurate non-linear mapping, and replaces the square filter and adaptive pixel compensation in the traditional filter, so as to realize video filtering

Images