Improved 3D video synthesis combining graph cuts and chroma key technology

Depth information is essential for 3DTV applications, as it is used for rendering in many modern 3D displays. In this paper, we propose a new approach for 3DTV content synthesis, by integrating an existing state-of-the-art MRF-based disparity estimation method with additional pre- and post-processing steps. The key of the proposed method is the decomposition of the scene in foreground and background. To this end, chroma key technology is used to facilitate the detection of foreground objects and to significantly improve depth estimation for these objects. Then, we can combine the foreground objects with any background, for both color images and depth maps, to generate a new representation of the scene. Experimental results have shown that the proposed approach can produce satisfactory depth maps with improved silhouettes for foreground objects and a stable background for all the frames of the sequence.