Wednesday, 25 July 2012
Is it possible to reconstruct a high-resolution picture from a pixelated source image? Yes, it is with a technique called super-resolution. 'Super-Resolution From a Single Image' is a research paper by computer scientists from the Weizmann Institute of Science in Israel.
Their approach is based on the observation that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Recurrence of patches within the same image scale gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution.