Image super-resolution reconstruction based on adaptive interpolation norm regularization

An image super-resolution reconstruction algorithm is proposed based on adaptive interpolation norm regularization, which can not only preserve more details near image edges than Tikhonov regularization, but also efficiently alleviate the staircasing of total variation regularization on flat regions. Furthermore, we propose the use of regularization functional instead of a constant regularization parameter. The regularization functional is defined in terms of the restored image at each iteration step, therefore allowing for the simultaneous determination of its value and the restoration of the degraded image. The iteration scheme, convergence and control function are thoroughly studied. Experimental results demonstrate the power of the proposed method.