Virtual view synthesis for multi-view video plus depth sequences using spatial-temporal information

To reduce the transmission bitrate, virtual view synthesis is an important technique for three-dimensional television (3DTV) and free viewpoint television (FTV) applications. The main aim of virtual view is to synthesize the virtual view sequence of some viewpoint from multi-view video plus depth sequences taken by parallel or non-parallel cameras. In this study, the proposed virtual view synthesis approach for multi-view video plus depth sequences taken by parallel cameras consists of four main parts: (1) disparity map estimation, optimization, and 3D warping, (2) virtual view synthesis using spatial information, (3) virtual view synthesis using temporal information, and (4) optimal virtual view selection. Based on the experimental results, the virtual views of the proposed approach are better than those of two comparison approaches.