Noise Residual Learning for Noise Modeling in Distributed Video Coding
van Luong H, Forchhammer S (2012)
Publication Language: English
Publication Type: Conference contribution
Publication year: 2012
Pages Range: 157-160
Event location: Krakow
ISBN: 978-1-4577-2049-9
URI: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6213310
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.
Authors with CRIS profile
How to cite
APA:
van Luong, H., & Forchhammer, S. (2012). Noise Residual Learning for Noise Modeling in Distributed Video Coding. In Proceedings of the Picture Coding Symposium (pp. 157-160). Krakow, PL.
MLA:
van Luong, Huynh, and S. Forchhammer. "Noise Residual Learning for Noise Modeling in Distributed Video Coding." Proceedings of the Picture Coding Symposium, Krakow 2012. 157-160.
BibTeX: Download