Superpixel-Based Disocclusion Filling in Depth Image Based Rendering

We present a new superpixel-based spatio-temporal disocclusion filling algorithm for view synthesis in Depth Image Based Rendering. When rendering new views from a single video-plus-depth sequence, background regions get exposed in the virtual view that are occluded in the video stream. To fill these regions we propose to use texture information that is found both in the current and in temporally neighboring frames. Instead of using a patch-based search for texture to fill the holes, we propose a new superpixel-based filling method that exploits the property of superpixels being more meaningful sub-entities of an image than simple square patches. We present experiments with both real and synthetic sequences to evaluate our proposed method.