Single image super-resolution based on subpixel shifting model

This paper presents a novel single image super-resolution (SR) reconstruction method using shifted kernel regression. Assuming that a low-resolution (LR) image is made by the shifted regression-based image degradation model, the proposed SR process shifts pixels in a regularly sampled LR image with a subpixel precision according to local gradient. The optimum displacement of each pixel is estimated using the Gaussian filtered second derivatives. The shifted low-resolution image is finally up-scaled by estimating the regression coefficients of the shifted kernels in the spatially adaptive manner. Experimental results show that the proposed method overcomes the limitation of existing intensity-based SR algorithms. The proposed SR algorithm can successfully restore sharp, clear edges without undesired artifacts such as ringing, inverted gradient, halo effects, etc. Without using an iterative process, the proposed single image SR algorithm can easily be implemented in the form of either pre- or post-processing filters for further enhancing the SR result of existing methods.