MIT project transforms selfies into pro-style portraits
As it stands, you can spice up your selfies with Instagram filters and other edits before beaming to the interwebs. But what about making a truly compelling smartphone self-portrait? Well, a team of researchers from MIT -- alongside folks from Adobe and the University of Virginia -- created an algorithm that could allow you to accurately apply the stylings of critically-acclaimed portrait photographers to everyday self-made snapshots. According to MIT grad student YiChang Shih, "style transfer" from the likes of Instagram and other filter-applying apps isn't well-suited for complementing facial features. Instead, this software uses existing works (Richard Avedon, Diane Arbus, and Martin Schoeller are cited as examples) and makes an appropriate match with the captured image. Eyes, beard, skin and lighting are all compared to make an ideal pairing before applying the artistic details. "You can't get stylizations that are this strong with those kinds of filters," says Adobe's Robert Bailey. "You can take a photo that has relatively flat lighting and bring out portrait-style pro lighting on it and remap the highlights as well."
