Hybrid method for image super-resolution using steering kernel regression and example-based approaches

A hybrid method for image super-resolution consisting of steering kernel regression (SKR) and example based super-resolution (EBSR) techniques has been proposed. In this model the output of SKR is given as the input to the EBSR module. It is observed that though the image super-resolution performed by SKR gives a reasonable result, in terms of perceptual quality, the regression techniques have inherent disadvantage of generating artifacts. EBSR on the other hand augments the image with high frequency information to the image, thereby sharpening the edges. In this paper, we demonstrate that the proposed hybrid scheme performs better than the individual methods described above.