Dual Learning-based Video Coding with Inception Dense Blocks

Chao Liu, Heming Sun, Jun'An Chen, Zhengxue Cheng, Masaru Takeuchi, Jiro Katto, Xiaoyang Zeng, Yibo Fan

研究成果: Conference contribution

4 被引用数 (Scopus)


In this paper, a dual learning-based method in intra coding is introduced for PCS Grand Challenge. This method is mainly composed of two parts: intra prediction and reconstruction filtering. They use different network structures, the neural network-based intra prediction uses the full-connected network to predict the block while the neural network-based reconstruction filtering utilizes the convolutional networks. Different with the previous filtering works, we use a network with more powerful feature extraction capabilities in our reconstruction filtering network. And the filtering unit is the block-level so as to achieve a more accurate filtering compensation. To our best knowledge, among all the learning-based methods, this is the first attempt to combine two different networks in one application, and we achieve the state-of-the-art performance for AI configuration on the HEVC Test sequences. The experimental result shows that our method leads to significant BD-rate saving for provided 8 sequences compared to HM-16.20 baseline (average 10.24% and 3.57% bitrate reductions for all-intra and random-access coding, respectively). For HEVC test sequences, our model also achieved a 9.70% BD-rate saving compared to HM-16.20 baseline for allintra configuration.

ホスト出版物のタイトル2019 Picture Coding Symposium, PCS 2019
出版社Institute of Electrical and Electronics Engineers Inc.
出版ステータスPublished - 2019 11月
イベント2019 Picture Coding Symposium, PCS 2019 - Ningbo, China
継続期間: 2019 11月 122019 11月 15


名前2019 Picture Coding Symposium, PCS 2019


Conference2019 Picture Coding Symposium, PCS 2019

ASJC Scopus subject areas

  • 信号処理
  • ソフトウェア
  • メディア記述


「Dual Learning-based Video Coding with Inception Dense Blocks」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。