Reconstructing 2D images with natural neighbour interpolation

In this paper, we explore image reconstruction by natural neighbour interpo lation from irregularly spaced samples. We sample the image irregularly wit h techniques based on the Laplacian or the derivative in the direction of t he gradient. Local coordinates based on the Voronoi diagram are used in nat ural neighbour interpolation to quantify the "neighbourliness" of data site s. Then we use natural neighbour interpolation in order to reconstruct the image. The main result is that the image quality is always very good in the case of the sampling techniques based on the Laplacian.