Adaptive large scale artifact reduction in edge-based image super-resolution

The goal of multi-frame image super-resolution is to use information from low-resolution images to construct highresolution images. Current multi-frame image super-resolution methods are highly sensitive to prominent large scale artifacts found within the low-resolution images, leading to reduced image quality. This paper presents a novel adaptive approach to large scale artifact reduction in multi-frame image super-resolution. The proposed method adaptively selects information from the low-resolution images such that prominent large scale artifacts are rejected during the reconstruction of the high-resolution image. In addition, an efficient super-resolution algorithm based on the proposed artifact reduction method and edge-adaptive constraint relaxation is introduced. Experimental results show that the proposed super-resolution algorithm based on the proposed artifact reduction method improves the perceptual quality of the resultant high-resolution image both quantitatively and qualitatively when compared with standard super-resolution methods in situations where prominent large scale artifacts exist.