Virtual view synthesis using layered depth image generation and depth-based inpainting for filling disocclusions and translucent disocclusions

Suryanarayana M. Muddala, Mårten Sjöström, Roger Olsson
2016 Journal of Visual Communication and Image Representation  
This manuscript is published in the open archive of Mid Sweden University http://miun.diva-portal.org to ensure timely dissemination of scholarly and technical work. The manuscript is the version accepted for publication. It may contain minor deviations from the published version. © 2016 This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/ The published version is available at Muddala, S.; Sjöström, M.; Olsson, R., "
more » ... l view synthesis using layered depth image generation and depth-based inpainting for filling disocclusions and translucent disocclusions," Abstract View synthesis is an efficient solution to produce content for 3DTV and FTV. However, proper handling of the disocclusions is a major challenge in the view synthesis. Inpainting methods offer solutions for handling disocclusions, though limitations in foreground-background classification causes the holes to be filled with inconsistent textures. Moreover, the state-of-the art methods fail to identify and fill disocclusions in intermediate distances between foreground and background through which background may be visible in the virtual view (translucent disocclusions). Aiming at improved rendering quality, we introduce a layered depth image (LDI) in the original camera view, in which we identify and fill occluded background so that when the LDI data is rendered to a virtual view, no disocclusions appear but views with consistent data are produced also handling translucent disocclusions. Moreover, the proposed foreground-background classification and inpainting fills the disocclusions with neighboring background texture consistently. Based on the objective and subjective evaluations, the proposed method outperforms the state-of-the art methods at the disocclusions.
doi:10.1016/j.jvcir.2016.02.017 fatcat:35mh6sad2nf2pctkcpbffyvk4a