Edge-preserving depth-image-based rendering method

Distribution of future 3DTV is likely to use supplementary depth information to a video sequence. New virtual views may then be rendered in order to adjust to different 3D displays. All depth-imaged-based rendering (DIBR) methods suffer from artifacts in the resulting images, which are corrected by different post-processing. The proposed method is based on fundamental principles of 3D-warping. The novelty lies in how the virtual view sample values are obtained from one-dimensional interpolation, where edges are preserved by introducing specific edge-pixels with information about both foreground and background data. This avoids fully the post-processing of filling cracks and holes. We compared rendered virtual views of our method and of the View Synthesis Reference Software (VSRS) and analyzed the results based on typical artifacts. The proposed method obtained better quality for photographic images and similar quality for synthetic images.