A Single-Image Super-Resolution Method
for Texture Interpolation
Yaron Kalit and Moshe Porat
In recent years a number of super-resolution techniques have been proposed. Most of these techniques construct a high resolution image by either combining several low resolution images at sub-pixel misalignments or by learning correspondences between low and high resolution image pairs. In this paper we present a stochastic super-resolution method for color textures from a single image. The proposed algorithm takes advantage of the repetitive nature of textures, and the fact that for most texture patches several instances of similar patches exist within the image. In the first step of the algorithm the intensity component is interpolated. For each pixel, a probability distribution of gray level values is constructed from the distances to other patches in the texture as well as from local features and patch color similarity. The intensity value of the interpolated pixel is then chosen according to the probability distribution. In the second stage, the color components are interpolated in a similar manner, using quantized patches of the color channels as well as the interpolated intensity values. Our conclusion is that the proposed approach outperforms presently available methods.