Facebook researchers are finally finding ways to fix accidental blinking photos of users through artificial intelligence (AI).
As reported by Techspot.com, Facebook researchers Brian Dolhansky and Cristian Canton Ferrer published a paper outlining a a machine-learning technique that can open blinked eyes when a photo was taken using generative adversarial networks (GANs).
In their paper titled “Eye In-Painting with Exemplar Generative Adversarial Networks,” the researchers explained how “exemplar GANs” (ExGANs) are used to paint on eyes of a subject based on the person’s photos with their eyes open. The network “trains” on the photos in order to re-create realistic-looking eyes to in-paint on the picture.
Dolhansky and Ferrer stated: “We show that ExGANs can produce photo-realistic personalized in-painting results that are both perceptually and semantically plausible by applying them to the task of closed-to-open eye in-painting in natural pictures.”
The results however are more effective with straight on shots. The system also still struggles with some photo aspects such as eyeglasses, profile or semi-profile shots, and long fringes.
The system is still in the research phase and Facebook has not released a marketing plan for it yet.
(Photo source: lifewire.com/ techspot.com)