Compressed Video Quality Enhancement with Temporal Group Alignment and Fusion

TL;DR

This paper introduces a novel neural network that enhances compressed video quality by leveraging long- and short-term temporal correlations through group alignment and fusion techniques.

Contribution

The paper presents a new temporal group alignment and fusion network with modules for intra-group alignment, inter-group fusion, and feature enhancement, improving video quality over prior methods.

Findings

Achieves up to 0.05dB quality gain

Reduces computational complexity

Outperforms state-of-the-art methods

Abstract

In this paper, we propose a temporal group alignment and fusion network to enhance the quality of compressed videos by using the long-short term correlations between frames. The proposed model consists of the intra-group feature alignment (IntraGFA) module, the inter-group feature fusion (InterGFF) module, and the feature enhancement (FE) module. We form the group of pictures (GoP) by selecting frames from the video according to their temporal distances to the target enhanced frame. With this grouping, the composed GoP can contain either long- or short-term correlated information of neighboring frames. We design the IntraGFA module to align the features of frames of each GoP to eliminate the motion existing between frames. We construct the InterGFF module to fuse features belonging to different GoPs and finally enhance the fused features with the FE module to generate high-quality video frames. The experimental results show that our proposed method achieves up to 0.05dB gain and lower complexity compared to the state-of-the-art method.