Noise Residual Learning for Noise Modeling in Distributed Video Coding

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Standard

Noise Residual Learning for Noise Modeling in Distributed Video Coding. / Luong, Huynh Van; Forchhammer, Søren.

2012 Picture Coding Symposium. IEEE, 2012. p. 157-160.

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Harvard

APA

CBE

Luong HV, Forchhammer S. 2012. Noise Residual Learning for Noise Modeling in Distributed Video Coding. In 2012 Picture Coding Symposium. IEEE. pp. 157-160. Available from: 10.1109/PCS.2012.6213310

MLA

Vancouver

Luong HV, Forchhammer S. Noise Residual Learning for Noise Modeling in Distributed Video Coding. In 2012 Picture Coding Symposium. IEEE. 2012. p. 157-160. Available from: 10.1109/PCS.2012.6213310

Author

Luong, Huynh Van; Forchhammer, Søren / Noise Residual Learning for Noise Modeling in Distributed Video Coding.

2012 Picture Coding Symposium. IEEE, 2012. p. 157-160.

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Bibtex

@inbook{7df48b0b70d042a380d2fc1849999de3,
title = "Noise Residual Learning for Noise Modeling in Distributed Video Coding",
keywords = "Distributed Video Coding, Noise residual learning, Adaptive noise model",
publisher = "IEEE",
author = "Luong, {Huynh Van} and Søren Forchhammer",
year = "2012",
doi = "10.1109/PCS.2012.6213310",
isbn = "978-1-4577-2049-9",
pages = "157-160",
booktitle = "2012 Picture Coding Symposium",

}

RIS

TY - GEN

T1 - Noise Residual Learning for Noise Modeling in Distributed Video Coding

A1 - Luong,Huynh Van

A1 - Forchhammer,Søren

AU - Luong,Huynh Van

AU - Forchhammer,Søren

PB - IEEE

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

KW - Distributed Video Coding

KW - Noise residual learning

KW - Adaptive noise model

U2 - 10.1109/PCS.2012.6213310

DO - 10.1109/PCS.2012.6213310

SN - 978-1-4577-2049-9

BT - 2012 Picture Coding Symposium

T2 - 2012 Picture Coding Symposium

SP - 157

EP - 160

ER -