A novel fusion method for 3d-tv view synthesis using temporal and disparity correlations

Abstract

Abstract: View synthesis like depth-image-based rendering (DIBR) plays a significant role in content creation for three-dimensional television. However, perceptual errors introduced by current view synthesis often result in severe distortions in synthesized images. In this paper, we propose a novel view synthesis fusion (VSF) method that adaptively exploits temporal and disparity correlations to improve the quality of the synthesized picture. The proposed VSF method defines a robust correlation assessment metric for fusing several pre-created virtual-view candidates. Unlike conventional methods, the proposed fusion algorithm is applied to both hole and non-hole areas. Experimental results show the proposed method significantly outperforms in peak signal-to-noise ratio (PSNR) and subjective visual quality, compared to other conventional methods. © 2020 Institute of Electronics and Information Engineers. All rights reserved.