Researchers Use AI to Boost Metalens Camera Image Quality

In a new study, researchers were able to improve the low-quality images produced by a metalens. These types of ultra-thin cameras have the advantage of being small, but typically have poor image quality. That may be changing.

AI enhancement of photos is not new, but using them to improve the low quality of metalenses is.

“Metalenses are ultrathin optical devices — often just a fraction of a millimeter thick — that use nanostructures to manipulate light,” as a release regarding the study explains. The technology opens up a future where cameras would be far smaller and lighter, also creating more opportunities for mobile photography innovation. But that minuscule means metalenses are nearly as good as traditional optical lenses.

“Our technology allows our metalens-based devices to overcome the limitations of image quality,” research team leader Ji Chen from Southeast University in China said in a release. “This advance will play an important role in the future development of highly portable consumer imaging electronics and can also be used in specialized imaging applications such as microscopy.”

In the study, which was published in the journal Optics Letters, researchers “used a type of machine learning known as a multi-scale convolutional neural network to improve resolution, contrast and distortion in images from a small camera … they created by directly integrating a metalens onto a CMOS imaging chip.”

With this development, images taken using metalens cameras might finally be able to compete with the quality of those captured using typical optical lenses. Once that happens, it could shake up the camera industry similarly to the advent of mass-produced digital cameras. For example, mobile phone lenses, already quite closely matched to proper cameras these days, could start edging closer to image quality seen from professional-level gear. That could all happen without the need to expand the current sizes of smartphones.

“Metalens-integrated cameras can be directly incorporated into the imaging modules of smartphones, where they could replace the traditional refractive bulk lenses,” Chen added in the release. “They could also be used in devices such as drones, where the small size and lightweight camera would ensure imaging quality without compromising the drone’s mobility.”

It will be interesting to see how metalens technology and the use of machine learning to improve images from these cameras evolves. While this latest study focuses on AI to clean up results, other work is being done to advance metalenses themselves, too.

Image credits: Optica Letters