Distributed multiview video coding using the fusion of triple side information

Traditional multiview video coding schemes exploit all types of correlations at the encoder. The inherent high encoder complexity and the needs for large volume data communication between cameras make them impractical for many applications. In this paper, we propose a novel distributed coding scheme for multiview video. All the views are separately encoded but jointly decoded. At the decoder, we design a fusion algorithm that is able to make full use of three types of side information: temporal prediction, interview motion prediction and inter-view luma prediction. This is the key innovation in this research. This fusion scheme is able to exploit both intra-view and inter-view correlations with a low complexity encoder. Experimental results indicate significant R-D performance gain over single view distributed video coding and traditional intra coding.