An approach to 2D-To-3D conversion for multiview displays

This paper proposes an approach for 2D-to-3D conversion for multiview displays. It employs an object-based approach where objects at large depth differences are first segmented by semi-automatic tools. Appropriate depth values are assigned to these objects and the missing image pixels at the background are filled in by inpainting techniques so that different views of the image can be synthesized. This approach helps to shorten the process of 2D-to-3D conversion and its performance is satisfactory for images and short video clips.