Gradient guided image interpolation

In this paper, we propose a novel edge prior for image interpolation which assumes that the variation of image intensity away from an edge is locally similar along the edge. Based on this edge prior, our method first approximates the gradient of the HR image which is then refined by diffusion. The unknown HR pixels are estimated by a weighted average of their neighbouring LR samples, with the weights being determined with respect to the gradient. This new approach performs significantly better than several representative edge-directed image interpolation methods in terms of PSNR and SSIM, as well as subjective visual quality in most of our test cases. Annoying artifacts (such as blurring, jaggies, ringing, etc.) are also greatly suppressed.