Video Compression based on Spatio-Temporal Resolution Adaptation

Mariana Afonso, Aaron Zhang, David Bull

Research output: Contribution to journalArticle (Academic Journal)peer-review

50 Citations (Scopus)
941 Downloads (Pure)

Abstract

A Video Compression framework based on Spatio-Temporal Resolution Adaptation (ViSTRA) is proposed, which dynamically resamples the input video spatially and temporally during encoding, based on a quantisation-resolution decision, and reconstructs the full resolution video at the decoder. Temporal upsampling is performed using frame repetition, whereas a Convolutional Neural Network (CNN) superresolution model is employed for spatial resolution upsampling. ViSTRA has been integrated into the High Efficiency Video Coding (HEVC) reference software (HM 16.14). Experimental results verified via an international challenge show significant improvements, with BD-rate gains of 15% based on PSNR and an average MOS difference of 0.5 based on subjective visual quality tests.
Original languageEnglish
Pages (from-to)275-280
Number of pages6
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume29
Issue number1
Early online date31 Oct 2018
DOIs
Publication statusPublished - 1 Jan 2019

Keywords

  • Video compression
  • spatial resolution adaptation
  • temporal resolution adaptation
  • perceptual video compression
  • CNN-based super-resolution

Fingerprint

Dive into the research topics of 'Video Compression based on Spatio-Temporal Resolution Adaptation'. Together they form a unique fingerprint.

Cite this