Adaptive Large Scale Artifact Reduction in Edge-based Image Super-Resolution

A. Wong and W. Bishop (Canada)

Keywords

artifact reduction, edgeadaptive, image superresolution.

Abstract

The goal of multi-frame image super-resolution is to use information from low-resolution images to construct high resolution images. Existing construction techniques are highly sensitive to prominent large scale artifacts in the low-resolution images. This paper presents a novel, adap tive approach to large scale artifact reduction in multi frame image super-resolution. The proposed method adap tively selects information from the low-resolution images such that prominent large scale artifacts are rejected dur ing the construction of high-resolution images. An efficient super-resolution algorithm that utilizes the proposed tech nique with an edge-adaptive constraint relaxation is intro duced. Experimental results demonstrate that the proposed algorithm improves the visual quality of the constructed high-resolution images when prominent large scale arti facts exist.

Important Links:



Go Back