ViSTRA3: Video coding with deep parameter adaptation and post processing

Chen Feng, Duolikun Danier, Charlie Tan, Fan Zhang, David Bull

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

Abstract / Description of output

This paper presents a deep learning-based video compression framework (ViSTRA3), which has been employed to generate compression results for the ISCAS 2022 Grand Challenge on Neural Network-based Video Coding. The proposed framework intelligently adapts video format parameters of the input video before encoding, subsequently employing a CNN at the decoder to restore their original format and enhance reconstruction quality. ViSTRA3 has been integrated with the H.266/VVC Test Model VTM 14.0, and evaluated under the Joint Video Exploration Team Common Test Conditions. Bjønegaard Delta (BD) measurement results show that the proposed framework consistently outperforms the original VVC VTM, with average BD-rate savings of 1.8% and 3.7% based on the assessment of PSNR and VMAF.
Original languageEnglish
Title of host publication2022 IEEE International Symposium on Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers
Pages824-828
Number of pages5
ISBN (Electronic)9781665484855
ISBN (Print)9781665484862
DOIs
Publication statusPublished - 11 Nov 2022
Event2022 IEEE International Symposium on Circuits and Systems - Austin, United States
Duration: 28 May 20221 Jun 2022

Publication series

NameProceedings of the IEEE International Symposium on Circuits and Systems
PublisherIEEE
ISSN (Print)0271-4302
ISSN (Electronic)2158-1525

Symposium

Symposium2022 IEEE International Symposium on Circuits and Systems
Abbreviated titleISCAS 2022
Country/TerritoryUnited States
CityAustin
Period28/05/221/06/22

Keywords / Materials (for Non-textual outputs)

  • video coding
  • three-dimensional displays
  • circuits and systems
  • video compression
  • feature extraction
  • encoding
  • decoding

Fingerprint

Dive into the research topics of 'ViSTRA3: Video coding with deep parameter adaptation and post processing'. Together they form a unique fingerprint.

Cite this