An Iterative Robust Kernel-Based Regression Method for Simultaneous Single Image Super-Resolution and Denoising

Abstract

In this paper, we present a uniform mathematical framework based on a robust kernel-based regression for the task of simultaneous single-image super-resolution and denoising. The given model is formulated as a convex 1 sparse optimization problem, which can be efficiently solved by the alternating direction method of multipliers (ADMM). Especially, the proposed method is applied to image patches to reduce computational time. Additionally, an iterative strategy is also incorporated into the approach to refine more image details. The extensive experiments on simulated natural images with additional sparse noise and real time-of-flight (ToF) images demonstrate the ability of simultaneously removing sparse noise and enhancing image resolution.INDEX TERMS Kernel-based regression, uniform mathematical framework, joint image super-resolution and denoising, ToF images.

Single Image Super-Resolution by Residual Recovery Based on an Independent Deep Convolutional Network

“…Based on the MAP, some regularization models are proposed for single image applications, e.g., image restoration [9]- [11], image super-resolution [12], [13]. In [12], Deng et al proposed a sparse regularization model by reproducing kernel Hilbert space (RKHS) function for single image SR.…”

“…Experimental results demonstrate that the regularization models could obtain promising performance. Wang et al in [13] proposed an RKHS-based regularization model which can realize image SR and denoising simultaneously. Dictionary-based learning approaches play a crucial role in the field of image SR, as well as show significant improvements than classical methods.…”