Compressed video quality enhancement method based on attention mechanism and time dependence

Abstract

The invention belongs to the technical field of digital video processing, and particularly relates to a compressed video quality enhancement method based on an attention mechanism and time dependence.The method comprises the steps of constructing an FAM module based on an attention mechanism; constructing an inter-frame long-term time dependency relationship guided LDE feature fusion module; constructing a fine RSDE feature fusion module guided by an inter-frame short-term time dependence relationship; obtaining feature information endowed with different attention by using an FAM module according to contributions of a plurality of input continuous frames; extracting long-term time dependence information from the features between the adjacent frames by using an LDE module to obtain an intermediate result and feature information; and finally, selectively extracting a short-term time dependency relationship from the previous enhanced frame by combining the FAM module and the RSDE moduleto generate a final enhancement result. Experiments show that the visual quality can be enhanced on a test set containing various real scenes, and the objective quality evaluation index is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of digital video intelligent processing, and in particular relates to a method for enhancing video quality. Background technique [0002] With the continuous development of computer technology and network communication technology, a large amount of video information floods into the Internet, which brings great challenges to the current storage and transmission technology. Therefore, various video compression technologies emerge as the times require, such as MPEG (Moving Picture Experts Group), HEVC (High Efficiency Video Coding) [2] standards, etc. However, these video information are compressed lossily to achieve a higher compression rate, so that the decompressed video will always lose some important high-frequency information, and produce some artifacts such as blockiness and ringing, which lead to its Visual quality is severely degraded. [0003] Compressed video quality enhancement method (Quality enh...

AI Technical Summary

Problems solved by technology

[0005] However, these methods have their own disadvantages. The first method must use the reference information attached to the decoder, and this information cannot be obtained in most practical application scenarios, which makes this method have certain limitations.

In the second method, it is difficult to train a network to distinguish between good and bad quality based on the subtle objective quality gap between adjacent frames, which will undoubtedly produce many unnecessary errors. There will always be a certain time interval between frames, that is, there will be greater motion between multiple frames as input to the network, which also greatly increases the difficulty of network training

Images