Single image super-resolution via l 0 image smoothing

Abstract

We propose a single image super-resolution method based on a L 0 smoothing approach. We consider a low-resolution image as two parts: one is the smooth image generated by the L 0 smoothing method and the other is the error image between the low-resolution image and the smoothing image. We get an intermediate high-resolution image via a classical interpolation and then generate a high-resolution smoothing image with sharp edges by the L 0 smoothing method. For the error image, a learning-based super-resolution approach, keeping image details well, is employed to obtain a high-resolution error image. The resulting high-resolution image is the sum of the high-resolution smoothing image and the high-resolution error image. Experimental results show the effectiveness of the proposed method.