Artificial intelligence makes blurry faces look more than 60 times sharper

Duke University researchers have developed an AI tool that can turn blurry, unrecognizable pictures of people's faces into eerily convincing computer-generated portraits, in finer detail than ever before. 

Previous methods can scale an image of a face up to eight times its original resolution. But the Duke team has come up with a way to take a handful of pixels and create realistic-looking faces with up to 64 times the resolution, 'imagining' features such as fine lines, eyelashes and stubble that weren't there in the first place.

"Never have super-resolution images been created at this resolution before with this much detail," said Duke computer scientist Cynthia Rudin, who led the team.



One of the core foundations of artificial intelligence is mathematics. Therefore, if artificial intelligence wants to develop better, it must first solve the basic problems of mathematics; at the same time, the development of artificial intelligence has also played an important role in promoting mathematical researches.

Journal of Probe - Mathematics & Mathematical Sciences is a peer-reviewed, international journal that focuses on all areas related to mathematics. It includes the numerical analysis, biomathematics, dynamical systems, fluid dynamics, and mathematical physics and so on.

The journal accepts original research articles, review articles, case reports and short communications. Researchers, scholars, teachers and advanced students in the field of mathematics are expected to submit their papers!

Access more details about this journal at: