• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2019 年度 実績報告書

深層学習による主観的高画質化を目指した新しい圧縮技術の研究

研究課題

研究課題/領域番号 19J14620
研究機関早稲田大学

研究代表者

CHENG ZHENGXUE  早稲田大学, 理工学術院, 特別研究員(DC2)

研究期間 (年度) 2019-04-25 – 2021-03-31
キーワード画像圧縮 / 深層学習 / 高画質化
研究実績の概要

最近超高解像度、360度といったマルチメディアコンテンツのさらなる大容量化に伴い、より高効率な圧縮技術が求められている。令和1年度は、前述した目的を達成するために、従来の映像符号化標準に従い、提案するユーザーの感じる主観画質の高画質化を目的とし、CVPRとICIP国際学会で筆頭著者として発表を行うと共に、査読付き論文誌と令和2年度の国際学会ICASSPとCVPRへの採択が確定していた。

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

So far, the progress is conducted smoothly according to my plan. I have finished my target in the first year. And I have seperate my goals and future plan into two parts as followed.
Regarding deep learning based lossy image compression, I have reached a milestone, that is, reaching the performance of HEVC on both objective quality metrics and subjective quality, and the next plan for is to outperform VVC. Besides, some of our experiments have validate the possibility to achieve this target.
Regarding deep learning based lossy video compression, I have reached a milestone to achieve comparable performance with H.264. The next step is to outperform HEVC, or even VVC. Specially, my plan is to develop better P-frame prediction and B-frame prediction algorithms and incorporate them into inter-encoded video compression algorithms.

今後の研究の推進方策

To promote the development of research, we are considering the following two strategies.
The first is to promote the learned image compression. I will develop a better entropy model by extending current single Gaussian to Gaussian mixture likelihoods. Second, I will enhance the network structure by consider some novel modules such as attention. The CVPR, a flagship meeting in the field of computer vision will have the event "Workshop and Challenge on Learned Image Compression” (CLIC) and I will participate in the challenge. Not only I can compare my results with research teams from other universities and companies, but also I could compare with conventional compression standards, because some hybrid methods are also submitted to this challenge.
The second is to enhance the performance of learned video compression. My plan is to enhance the overall performance module-by-module. Then what I can do include the better video prediction (P-frames) algorithms, better video interpolation algorithms (B-frames) and better network to encode residual and motion vectors etc. Based on the knowledge of learned image compression, I can extend the entropy models to videos and combine all these modules together. Finally, I can achieve better results than my current result.
Finally, through this research and development, we can contribute to the further development of compression technology.

  • 研究成果

    (9件)

すべて 2020 2019

すべて 雑誌論文 (5件) (うち国際共著 5件、 査読あり 5件) 学会発表 (4件) (うち国際学会 3件)

  • [雑誌論文] Energy Compaction-Based Image Compression Using Convolutional AutoEncoder2020

    • 著者名/発表者名
      Zhengxue Cheng, Heming Sun, Masaru Takeuchi, Jiro Katto
    • 雑誌名

      IEEE Transactions on Multimedia

      巻: 22 ページ: 860-873

    • DOI

      10.1109/TMM.2019.2938345

    • 査読あり / 国際共著
  • [雑誌論文] Enhanced Intra Prediction for Video Coding by Using Multiple Neural Networks2020

    • 著者名/発表者名
      Heming Sun, Zhengxue Cheng, Masaru Takeuchi, Jiro Katto
    • 雑誌名

      IEEE Transactions on Multimedia

      巻: NA ページ: 1-14

    • DOI

      10.1109/TMM.2019.2963620

    • 査読あり / 国際共著
  • [雑誌論文] Methods for Adaptive Video Streaming and Picture Quality Assessment to Improve QoS/QoE Performances2019

    • 著者名/発表者名
      Kenji Kanai, Bo Wei, Zhengxue Cheng, Masaru Takeuchi and Jiro Katto
    • 雑誌名

      IEICE Transactions on Communications

      巻: E102.B ページ: 1240-1247

    • DOI

      https://doi.org/10.1587/transcom.2018ANI0003

    • 査読あり / 国際共著
  • [雑誌論文] Perceptual Quality Study on Deep Learning Based Image Compression2019

    • 著者名/発表者名
      Zhengxue Cheng, Pinar Akyazi, Heming Sun, Jiro Katto, Touradj Ehrahimi
    • 雑誌名

      Proceedings of IEEE International Conference on Image Processing (ICIP)

      巻: 1 ページ: 1-5

    • DOI

      10.1109/ICIP.2019.8803824

    • 査読あり / 国際共著
  • [雑誌論文] Learning Image and Video Compression through Spatial-Temporal Energy Compaction2019

    • 著者名/発表者名
      Zhengxue Cheng, Heming Sun, Masaru Takeuchi, Jiro Katto
    • 雑誌名

      Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

      巻: 1 ページ: 1-10

    • DOI

      10.1109/CVPR.2019.01031

    • 査読あり / 国際共著
  • [学会発表] Perceptual Quality Study on Deep Learning based Image Compression2020

    • 著者名/発表者名
      Zhengxue Cheng
    • 学会等名
      2020年電子情報通信総合大会
  • [学会発表] Perceptual Quality Study on Deep Learning Based Image Compression2019

    • 著者名/発表者名
      Zhengxue Cheng
    • 学会等名
      IEEE International Conference on Image Processing (ICIP)
    • 国際学会
  • [学会発表] Learning Image and Video Compression through Spatial-Temporal Energy Compaction2019

    • 著者名/発表者名
      Zhengxue Cheng
    • 学会等名
      2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 国際学会
  • [学会発表] Deep Residual Learning for Image Compression2019

    • 著者名/発表者名
      Zhengxue Cheng
    • 学会等名
      2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop
    • 国際学会

URL: 

公開日: 2021-01-27  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi