A learning-based low complexity in-loop filter for video coding

Chao Liu, Heming Sun, Jiro Katto, Xiaoyang Zeng, Yibo Fan

研究成果: Conference contribution

抄録

With the continuous development of mobile devices, it becomes possible for people to demand higher definition videos. To alleviate the pressure of deploying the video codec in mobile multimedia, a learning-based low complexity in-loop filter is proposed in this paper. Depthwise separable convolution is combined with batch normalization to construct this model. To enhance its performance, the knowledge from a pre-trained teacher model is transferred to it. However, the over-smoothing problem in the inter frames caused by double enhancing effect remains. To solve this, a Wiener-based filtering algorithm that tries to restore the distortion from the learned residuals is designed and introduces an adequate filtering effect. The experimental results show that our proposed methods achieve considerable BD-rate reduction than HEVC anchor. Compared with the previous state-of-the-art work VR-CNN, our model achieves 1.65% extra BD-rate reduction, 79.1% decrease in FLOPs, 25% decrease in encoding complexity, and 70% decoding complexity decrease.

本文言語English
ホスト出版物のタイトル2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781728114859
DOI
出版ステータスPublished - 2020 7
イベント2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020 - London, United Kingdom
継続期間: 2020 7 62020 7 10

出版物シリーズ

名前2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020

Conference

Conference2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020
国/地域United Kingdom
CityLondon
Period20/7/620/7/10

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ネットワークおよび通信
  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識
  • メディア記述

フィンガープリント

「A learning-based low complexity in-loop filter for video coding」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル