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. Existing construction techniques are highly sensitive to prominent large scale artifacts in the low-resolution images. This paper presents a novel, adaptive approach to large scale artifact reduction in multiframe image super-resolution. The proposed method adaptively selects information from the low-resolution images such that prominent large scale artifacts are rejected during the construction of high-resolution images. An efficient super-resolution algorithm that utilizes the proposed technique with an edge-adaptive constraint relaxation is introduced. Experimental results demonstrate that the proposed algorithm improves the visual quality of the constructed high-resolution images when prominent large scale artifacts exist.