Single frame super-resolution using multiple graph structured program
Yusuke Natsui, Tomoharu Nagao · 2016
Single frame Super-Resolution (SR) is a technique to generate a high-resolution (HR) image from one low-resolution (LR) image. Generally, single frame SR has trade-off between image quality and computational cost. In this paper, we propose a single frame SR method using multiple graph structured programs based on Cartesian Genetic Programming (CGP). In order to improve the trade-off, we use low computational cost graphs which are constructed from HR and LR images. We constructed each graph structured program simultaneously. Experimental result shows the effectiveness of combining multiple graph structured programs. We present a fast and good quality SR method using multiple programs.