In this paper, we propose a robust image super-resolution algorithm, which aims to maximize the overall visual quality of super-resolution results. We consider a good super-resolution algorithm to be fidelity preserving, image detail enhancing and smooth. Accordingly, we define perception-based measures for these visual qualities. Based on these quality measures, we formulate image super-resolution as an optimization problem aiming to maximize the overall quality. Since the quality measures are quadratic, the optimization can be solved efficiently. Experiments on a large image set and subjective user study demonstrate the effectiveness of the perception-based quality measures and the robustness and efficiency of the presented method.

@Article{LWZGG09,
  author       = "Liu, Feng and Wang, Jinjun and Zhu, Shenghuo and Gleicher, Michael and Gong, Yihong",
  title        = "Visual-Quality Optimizing Super Resolution",
  journal      = "Computer Graphics Forum",
  number       = "1",
  volume       = "28",
  pages        = "127--140",
  year         = "2009",
  url          = "http://graphics.cs.wisc.edu/Papers/2009/LWZGG09"
}