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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publication2019 Picture Coding Symposium, PCS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728147048
DOIs
Publication statusPublished - 2019 Nov
Event2019 Picture Coding Symposium, PCS 2019 - Ningbo, China
Duration: 2019 Nov 122019 Nov 15

Publication series

Name2019 Picture Coding Symposium, PCS 2019

Conference

Conference2019 Picture Coding Symposium, PCS 2019
CountryChina
CityNingbo
Period19/11/1219/11/15

Keywords

  • High Efficiency Video Coding (HEVC)
  • Neural Network
  • Reconstruction Filtering
  • Video Coding

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Media Technology

Fingerprint Dive into the research topics of 'Dual Learning-based Video Coding with Inception Dense Blocks'. Together they form a unique fingerprint.

  • Cite this

    Liu, C., Sun, H., Chen, JA., Cheng, Z., Takeuchi, M., Katto, J., Zeng, X., & Fan, Y. (2019). Dual Learning-based Video Coding with Inception Dense Blocks. In 2019 Picture Coding Symposium, PCS 2019 [8954498] (2019 Picture Coding Symposium, PCS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PCS48520.2019.8954498