Single Image Super Resolution Through Neighbor Embedding Based on Field of Experts
Mingming Cao -, Zongliang Gan, Xiuchang Zhu · International Journal of Digital Content Technology and its Applications · 2013
A parametric framework, called Field of Experts (FoE), has been proposed for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. In this paper we apply Field of Experts for the first time to the problem of single natural image super resolution through neighbor embedding, where we toke the coefficients of the linear filters learned by FoE as the feature vectors. Experimental results show that the proposed method not only achieve a better recovery of a single low resolution image comparing with state-of-the-art feature vectors, but also reduce the computational complexity.