Infoscience

Conference paper

Fast and Enhanced Algorithm for Exemplar Based Image Inpainting

Image Inpainting is referred to as the art of removing objects from the image in a visually plausible manner so that it seems reasonable to the human eye. There have been several approaches proposed for the same. In this paper, we present an algorithm that improves on a previously proposed algorithm and provides faster inpainting. Using our approach, one can inpaint small regions from the image as well as remove complete objects. The inpainting is based on the exemplar based approach. The basic aim of this approach is to find examples (i.e. patches) from the image and replace the lost data with it. Applications of this technique include the restoration of old photographs and damaged film; removal of superimposed text like dates, subtitles etc.; and the removal of entire objects from the image like microphones or wires in special effects. We obtained good quality results quickly using our approach.

Related material

Contacts

EPFL authors