Image Inpainting by Hyperbolic Selection of Pixels for Two-Dimensional Bicubic Interpolations

Image inpainting is a restoration process which has numerous applications. Some of the inpainting applications include restoring of a scanned version of an old image with scratches or removing objects in images. Different approaches have been used for implementation of inpainting algorithms. Interpolation approaches only consider one direction for this purpose. In this paper., we present a new perspective to image inpainting. We consider multiple directions and apply both one-dimensional bicubic and two-dimensional hyperbolic interpolations. Neighboring pixels are selected in a hyperbolic formation for better preservation of corner pixels. We compare our work with recent inpainting approaches to show our superior results.