Automatic retouch for cellphone images

The new system is a machine-learning system, meaning that it learns to perform tasks by analysing training data; in this case, it was trained on thousands of pairs of images, raw and retouched.

Massachusetts Institute of Technology, Google, artificial intelligence system, Image retouch function, automatic image retouch, MIT

Raw and retouched versions of an image. Source: MIT

Researchers from the Massachusetts Institute of Technology and Google have developed an artificial intelligence system that can automatically retouch images in the style of a professional photographer. It can run on a cellphone, and it’s so fast that it can display retouched images in real time, so that the photographer can see the final version of the image while still framing the shot, MIT News says on its website.

The work builds on an earlier project from the MIT researchers, in which a cellphone would send a low-resolution version of an image to a web server. The server would send back a “transform recipe” that could be used to retouch the high-resolution version of the image on the phone, reducing bandwidth consumption.

“Google heard about the work I’d done on the transform recipe,” MIT News quotes Michaël Gharbi, an MIT graduate student in electrical engineering and computer science and first author on both papers. “They themselves did a follow-up on that, so we met and merged the two approaches. The idea was to do everything we were doing before but, instead of having to process everything on the cloud, to learn it. And the first goal of learning it was to speed it up.”

The new system is a machine-learning system, meaning that it learns to perform tasks by analysing training data; in this case, it was trained on thousands of pairs of images, raw and retouched.

The researchers trained their system on a data set created by Durand’s group and Adobe Systems, the creators of Photoshop. The data set includes 5,000 images, each retouched by five different photographers. They also trained their system on thousands of pairs of images produced by the application of particular image-processing algorithms, MIT News says.

The system needed about 100 megabytes to execute its operations. “This technology has the potential to be very useful for real-time image enhancement on mobile platforms,” MIT News quotes Jon Barron, one of Gharbi’s colleagues on the study.