Hybrid motion/depth-oriented inpainting for virtual view synthesis in multiview applications

Abstract

Multiview video can provide users a 3D and virtual reality perception by its multiple viewing angles. To improve the quality of virtual view synthesized frame and remove the disocclusion region, hole filling technique is required. By classifying the different image artifact and applying proper hybrid motion/depth-oriented inpainting algorithm, the image quality will be closer to the real image. In addition, the simulation result and comparison with previous works on inpainting show that both objective evaluation estimates and subjective perceptual vision come to a better result by the system proposed in this paper.