Bayesian Anchored Neighborhood Regression for Single-Image Super-Resolution

Yinggan Tang, Ailian Fan

Abstract: Anchored neighborhood regression (ANR) single-image super-resolution (SISR) method demonstrates great superiority in speed and performance. However, ridge regression adopted by ANR didn’t take the prior knowledge of regression parameters into account, which easily leads to over-fitting and is not robust to noise. To mitigate this problem, a Bayesian ANR method is proposed for SISR, called B-ANR. B-ANR uses sparse Bayesian regression model to build the mapping relationship between the low resolution (LR) image patch and its neighbors. The parameters of Bayesian regression model as well as its variance are estimated using maximum a posterior. Since our proposed B-ANR is deduced in the probabilistic framework, it has stronger generalization performance and robustness to noise. Experimental results verify that our method is superior to ANR in performance.