Efficient Edge-Enhanced Super-resolution
Zoran A. Ivanovski, Ljupcho Panovski, Lina J. Karam, Macedonia Skopje · 2005
Abstract: A new approach for efficient and robust super-resolution is presented in this paper. The essence of the proposed method is in selectively applying a Bayesian MAP estimator to visually important image regions. Regions with high spatial activity are considered as visually important. The degree of image spatial activity is measured by calculating the gradient of the obtained estimate for the high-resolution image at each iteration. The results obtained through simulation and with real video exhibit a computational complexity reduction of up to 50%, along with improved visual quality and higher SNR gains for magnification factors equal to or higher than 4.