Filling Disocclusions in Extrapolated Virtual Views Using Hybrid Texture Synthesis

For glasses-free 3-D viewing, autostereoscopic displays provide a dense set of views showing a scene from slightly different viewpoints. As the number of views and their spatial positions are display dependent, a generic depth-enhanced multiview video plus depth format is used for coding and transmission. From this, the required views are generated via depth image-based rendering (DIBR) techniques by using original views and associated depth information. A critical problem in the DIBR techniques is that texture regions, which are covered by foreground objects in the original image, may become visible in the synthesized view, especially in extrapolation scenarios. To cover these disoccluded areas, a novel hybrid texture synthesis method is described in this paper. Our approach combines a new patch-based and a novel fast parametric texture synthesis method in an innovative way to compute the disoccluded image areas. The proposed method outperforms state-of-the-art approaches in terms of peak signal-to-noise ratio, structural similarity, visual saliency induced index, feature similarity index (color), and run-time.