Efficient CTU-based intra frame coding for HEVC based on deep learning

Zheng Teng Zhang, Chia Hung Yeh, Li Wei Kang, Min Hui Lin

研究成果: 書貢獻/報告類型會議論文篇章

9 引文 斯高帕斯(Scopus)

摘要

To further improve the compression efficiency of HEVC intra frame coding, in this paper, a deep learning-based framework is proposed. Inspired by recently developed deep learning models for image super-resolution (SR), we propose to train a CNN (convolutional neural network) model to precisely predict the residual information of each CTU (coding tree unit) at the HEVC encoder. As a result, better CTU reconstruction and better prediction for the compression of subsequent CTUs can be achieved. To reduce computational complexity, different from current CNN-based SR works, we propose to skip the non-linear mapping layer, and incorporate the residual learning to obtain better predicted residual for CTU encoding. Experimental results have shown that the proposed method achieves 3.2% bitrate reduction in average BDBR (Bjentegaard delta bit rate) with only 37% encoding complexity increased.

原文英語
主出版物標題Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
發行者Institute of Electrical and Electronics Engineers Inc.
頁面661-664
頁數4
ISBN(電子)9781538615423
DOIs
出版狀態已發佈 - 2018 二月 5
事件9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, 马来西亚
持續時間: 2017 十二月 122017 十二月 15

出版系列

名字Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
2018-February

會議

會議9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
國家/地區马来西亚
城市Kuala Lumpur
期間2017/12/122017/12/15

ASJC Scopus subject areas

  • 人工智慧
  • 人機介面
  • 資訊系統
  • 訊號處理

指紋

深入研究「Efficient CTU-based intra frame coding for HEVC based on deep learning」主題。共同形成了獨特的指紋。

引用此