Noise Residual Learning for Noise Modeling in Distributed Video Coding

Huynh Van Luong, Søren Forchhammer

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Distributed video coding (DVC) is a coding paradigm which exploits the source statistics at the decoder side to reduce the complexity at the encoder. The noise model is one of the inherently difficult challenges in DVC. This paper considers Transform Domain Wyner-Ziv (TDWZ) coding and proposes noise residual learning techniques that take residues from previously decoded frames into account to estimate the decoding residue more precisely. Moreover, the techniques calculate a number of candidate noise residual distributions within a frame to adaptively optimize the soft side information during decoding. A residual refinement step is also introduced to take advantage of correlation of DCT coefficients. Experimental results show that the proposed techniques robustly improve the coding efficiency of TDWZ DVC and for GOP=2 bit-rate savings up to 35% on WZ frames are achieved compared with DISCOVER.
Original languageEnglish
Title of host publication2012 Picture Coding Symposium
PublisherIEEE
Publication date2012
Pages157-160
ISBN (Print)978-1-4577-2049-9
ISBN (Electronic)978-1-4577-2048-2
DOIs
Publication statusPublished - 2012
EventPicture Coding Symposium 2012, PCS - Kraków, Poland
Duration: 7 May 20129 May 2012
http://www.pcs2012.org/

Conference

ConferencePicture Coding Symposium 2012, PCS
CountryPoland
CityKraków
Period07/05/201209/05/2012
Internet address

Keywords

  • Distributed Video Coding
  • Noise residual learning
  • Adaptive noise model

Cite this