PetaPixel

MIT Project Mimics Iconic Portrait Photogs, Takes Your Selfies to the Next Level

Are you not impressed with your average Instagram selfie? Is the lighting too bland and out of place for your liking? If so, a team made up of a researcher from MIT and a few individuals from Adobe and the University of Virginia might just have a solution to your problem.

They’ve created an algorithm capable of accurately stylizing an average, otherwise insignificant selfie to look like the works of some of the best-known and well-respected portrait photographers of all time.

MITPhotoReplication

As explained by MIT grad YiChang Shih, the program uses the works of Richard Avedon, Diane Arbus and Martin Schoeller (just to name a few) to inspire alterations that are then applied to the image being analyzed.

Once the standard snapshot is put through the software, the algorithm goes to work making sure eyes, skin, beards and lighting are as perfectly matched to an image in the archive as possible, stylizing the image accordingly. And although we don’t know exactly how the algorithm calculates and replicates the look of the images in their archive, it’s safe to say that it does an impressive (albeit a bit strange in some cases) job.

As to what these algorithms might turn into, Adobe’s Robert Bailey told TechCrunch that they’re, “looking at creating a consumer application utilizing the technology.” So watch out for this sort of capability in future iPhone and Android apps.

(via Engadget)