Gizmodo reporter Andrew Liszewski writes that MIT researchers have created an algorithm that can automatically fix warped faces in wide-angle shots without impacting the rest of the photo. Liszewski writes that the tool could “be integrated into a camera app and applied to wide angle photos on the fly as the algorithm is fast enough on modern smartphones to provide almost immediate results.”
Graduate students Ziv Epstein and Matt Groh have developed an AI system that adds spooky figures to photos, reports Mark Wilson for Fast Company. Wilson writes that the system “works so well because it places ghostly figures exactly where your brain naturally thinks they could be–on a path in the middle of a forest, rather than, say, floating randomly through the air.”
MIT researchers have created an AI system that allows users to automatically erase people and objects from photos, writes Mark Wilson for Fast Company. Wilson writes that the researchers have “built a remarkably simple front-end interface to control [the system]. In one column, you select what you’d like to remove from your photos, and in the right column, you select your source material.”
Researchers from MIT’s Camera Culture Group have devised a way for cameras to see through walls and bad weather, reports Vijee Venkatraman for BetaBoston. “It is not meant to be the next camera for consumers — the idea is to help with imaging in dangerous conditions, and to help with non-destructive testing,” writes Venkatraman.
MIT researchers have developed a new algorithm that can prevent overexposed photos, reports Devin Coldewey for NBC News. The algorithm reconstructs the “parts of the image that would have been too bright, recovering a blue sky or reflection on a shiny object.”
MIT researchers have developed a technique that can eliminate the washed-out spots found in overexposed images, reports Curt Woodward for BetaBoston. The technique could not only be used in photography, but could also be used for other applications like helping a “self-driving car stay on course despite quick light changes, such as entering a tunnel.”
MarketWatch reporter Sally French writes that researchers from MIT CSAIL have developed an algorithm that can be used to predict how memorable a person’s is. “The algorithm was created from a database of more than 2,000 images that were awarded a “memorability score” based on human volunteers’ ability to remember the pictures,” French writes.
“They've created an app which recasts mediocre headshots in the styles of famous portrait photographers like Richard Avedon and Diane Arbus- and in the process reveals how subtle shifts in lighting can completely change the way we perceive a face,” writes Boston Globe reporter Kevin Hartnett.