Super resolution via database-free texture synthesis

Image super resolution has been extensively investigated in the past decades. In this paper, we propose a super resolution algorithm which can provide vivid output image with rich details and sharp edges. The main contribution of this paper is the development of a database-free texture synthesis technique. Based on the fractal property of nature images, it is possible to find proper high-resolution patches in low-resolution input image itself. The double interpolation framework for up-sampling and the reconstruction constraint for the final optimization combined with the texture synthesis form the whole super resolution algorithm. Experimental results show that the proposed super resolution algorithm performs better and costs less time than other previous database-free super resolution works.