Quality-Gated Convolutional LSTM for Enhancing Compressed Video release_w5wilqhlsraexay4qsph3r6ezi

by Ren Yang, Xiaoyan Sun, Mai Xu, Wenjun Zeng

Released as a article .

2019  

Abstract

The past decade has witnessed great success in applying deep learning to enhance the quality of compressed video. However, the existing approaches aim at quality enhancement on a single frame, or only using fixed neighboring frames. Thus they fail to take full advantage of the inter-frame correlation in the video. This paper proposes the Quality-Gated Convolutional Long Short-Term Memory (QG-ConvLSTM) network with bi-directional recurrent structure to fully exploit the advantageous information in a large range of frames. More importantly, due to the obvious quality fluctuation among compressed frames, higher quality frames can provide more useful information for other frames to enhance quality. Therefore, we propose learning the "forget" and "input" gates in the ConvLSTM cell from quality-related features. As such, the frames with various quality contribute to the memory in ConvLSTM with different importance, making the information of each frame reasonably and adequately used. Finally, the experiments validate the effectiveness of our QG-ConvLSTM approach in advancing the state-of-the-art quality enhancement of compressed video, and the ablation study shows that our QG-ConvLSTM approach is learnt to make a trade-off between quality and correlation when leveraging multi-frame information. The project page: https://github.com/ryangchn/QG-ConvLSTM.git.
In text/plain format

Archived Files and Locations

application/pdf  2.3 MB
file_zajwrr4oxvekrjysi6uerz652i
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-04-14
Version   v3
Language   en ?
arXiv  1903.04596v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 1092e55d-a04d-4af0-a4b8-ba2baef5625b
API URL: JSON