Improved depth-image-based rendering algorithm

Abstract

The present work analyses a layered depth-image-basedrendering algorithm based on possible errors occurring with perspective 3D warping. The outcome is improvements to the algorithm that treats depth reliably for scenes containing several levels of foreground objects. The filling of holes of different kinds is addressed so that results have better visual quality. The analysis compares the results of the algorithm with a reference algorithm for the potential error types, and visual examples exhibit the consequences of the improvements. Different objective metrics give ambiguous results, which may be explained by the reduction of structure caused by the reference algorithm.

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

“…Ghosting artifacts are reduced by first detecting the depth discontinuities by estimating the FG and BG contribution and removing pixels in the vicinity of the discontinuities [11,12]. We can classify the hole-filling methods into two categories: Pre-processing and Post-processing.…”

“…Cracks are commonly avoided by interpolating the nearest pixel values [12]. Disocclusions are often filled with neighboring warped images in the case of view-interpolation (i.e., producing an intermediate view using its neighbors), whereas in the view-extrapolation case (i.e., using single view), the disocclusions problems need to be handled with only the information available in the original view.…”