Robust super-resolution for petite image sequences

This paper proposes a new, learning-based, two-step super-resolution (SR) algorithm well suited to solve the specially demanding problem of obtaining SR estimates from petite image sequences. The first step, devoted to increase the sampling rate of the incoming images, is performed by fitting linear combinations of functions generated from principal components (PC) to reproduce locally the sparse projected image data, and using these models to estimate image values at nodes of the high-resolution grid. PCs were obtained from local image patches sampled at sub-pixel level, which were generated in turn from a database of high-resolution images by application of a physically realistic observation model. Continuity between local image models is enforced by minimizing an adequate functional in the space of model coefficients. The second step, dealing with restoration, is performed by a linear filter with coefficients learned to restore residual interpolation artifacts in addition to low-resolution blurring, providing an effective coupling between both steps of the method. Results on a demanding five-image scanned sequence of graphics and text are presented, showing the excellent performance of the proposed method compared to several state-of-the-art two-step and Bayesian Maximum a Posteriori SR algorithms