2D to 3D Conversion in 3DTV Using Depth Map Generation and Virtual View Synthesis

Abstr act. 2D to 3D conversion is an important task in 3DTV due to the lack of 3D contents. In this paper, we propose a novel framework of the 2D to 3D video conversion. The proposed framework consists of two main stages: depth map generation and virtual view synthesis. In the depth map generation, motion and relative-height cues are effectively used to generate depth maps. In the virtual view synthesis, depth-image-based-rendering (DIBR) is adopted to generate the left and right virtual views from the depth maps. Experimental results demonstrate that the proposed 2D to 3D conversion is very effective in generating depth maps and providing realistic 3D effects.