Single Image Super Resolution Using Nearest Neighbor Local Gaussian Process Regression

The aim of signal image super resolution is to generate a high-resolution image from a given low-resolution (LR) input. Learning regression for low-high resolution patch pairs show promise in image super resolution. Gaussian process regression (GPR) is a typically probability model, has strong compatibility, but it is time consuming for building large numbers of samples modeling. In this paper, we extend a GPR based method and propose a nearest neighbor local Gaussian process regression (NNLGPR) that learns the function relationship from the low-resolution patch to the corresponding high frequency patch efficiently. At first, we search the nearest neighbor patches in the sample set for each input low resolution patch. Secondly, we establish local Gaussian process regression model from the searched nearest neighbor low-resolution patches to their corresponding high frequency patches for each low resolution patch. And then, the initial high resolution patch is restored by combining the up-scaled low-resolution patch with the high frequency patch. Finally, the non-local similarity and IBP are utilized to improve the quality of reconstruction image. Experimental results show that our approach acquires better results in the peak signal to noise ratio and the visual effects against several state of the arts methods.