One of the technologies that’s emerging in the camera world is using sensor-shifting to capture high-resolution photos. It involves shooting a sequence of shots with the sensor slightly shifted for each one, and then combining the photos into a high-res image. The new Olympus OM-D E-M5 II uses it to create 40MP photos using its 16MP sensor.
It turns out Apple has also been dabbling in the technology as well for its cameras, except with optical shifting instead of sensor shifting.
We’ve seen it in plenty of thriller/crime solver TV shows and movies: upon reviewing some grainy and very low-resolution surveillance footage, someone inevitably asks the technician, “can you zoom in on that and enhance it?” Then, with the quick press of a few masterfully placed keystrokes and bleepy computer sounds, the image is suddenly enhanced with vastly increased resolution and a key plot device is revealed.
“Super-Resolution From a Single Image” is an interesting research page by computer scientists over at the Weizmann Institute of Science in Israel. It details the group’s efforts to create sharp enlargements of small photographs, and offers comparisons between their algorithm and other popular ones being used and researched (e.g. nearest neighbor, bi-cubic). The large image of the baby seen above was created from the tiny image on the left. See if you can create something more useable using Photoshop.
Super-Resolution From a Single Image (via MetaFilter)