Updated June 2016
Y. Romano, J. Isidoro, and P. Milanfar,
"RAISR: Rapid and Accurate Image Super-Resolution
With sufficient training data (corresponding pairs of low and high resolution images) we can learn sets of filters (i.e. a mapping) that when applied to given image that is not in the training set, will produce a higher resolution version of it, where the learning is low complexity. In our approach, the run-time is more than one to two orders of magnitude faster than the best competing methods currently available, while producing results comparable or better than state-of-the-art.
H. Talebi and P. Milanfar,
"Fast Multi-layer Laplacian Enhancement
IEEE Transactions on Computational Imaging
, to appear
A novel, fast and practical way of enhancing images is introduced that builds on Laplacian operators of well-known edge-aware kernels, such as bilateral and nonlocal means, and extends these filters' capabilities. Multiple Laplacians of the affinity weights endow our method with progressive detail decomposition of the input image from fine to coarse scale. These image components are blended by a structure mask, which avoids noise/artifact magnification or detail loss in the output image.