Super-resolution for high-resolution displays
恭平 後藤, Fumiya Nagashima, Tomio Goto, Satoshi Hirano, Masaru Sakurai · 2014
We propose a super-resolution system for high-resolution displays that decomposes the input image into a structure component and a texture component using total variation regularization. The structure component is processed using a shock filter and the texture component is processed by a pulse enhancement filter. This system requires less computational time compared with learning-based systems and is suitable for moving pictures such as in televisions.