We’ve seen NVIDIA’s impressive content aware tool and noise removing tool. They have recently developed a generative adversarial network (GAN) which easily customizes styles of realistic faces and creates new faces. That’s right, these super-realistic faces you can see in the lead image are not real at all!
On 18 May this year, Taylor Swift’s fans could watch rehearsal clips at her concert at Los Angeles venue Rose Bowl. The clips were played at a special kiosk, but mesmerized fans had no idea that their photos were being taken by a facial recognition camera. The photos were cross-referenced with a database in Nashville, all in order to spot stalkers in case they appear at the concert.
Chinese company Xiaomi is working on an algorithm that will improve low-quality images. The company wants to compete with Apple regarding smartphone photography, and it has just published a new paper on the AI network called “DeepExposure.” It uses machine learning to improve low-quality images by adding them detail while enhancing colors and brightness.
Online bullying is a common problem today, and it’s not rare that social media users get death threats for all kinds of things. To help fight this, Instagram is turning to artificial intelligence. Over the upcoming weeks, Instagram will unroll the feature that will be able to automatically detect bullying in photos and their captions.
Someone took a perfect group photo of you and your friends. But oh no, you blinked. Well, Facebook is offering a solution to save a photo ruined by someone’s accidental blinking, so it becomes a social network material after all. They’ve published a research paper about a new method that uses AI to retouch closed eyes in photos.
If you’ve ever tried slowing down a video shot at 30 fps, you know that it becomes choppy and unusable. Nvidia has an AI-based solution for that which can turn your standard videos into watchable slow motion. The algorithm predicts what should come between two frames and fills in the space between them. As a result, you can get perfectly usable slow motion videos even if they were shot at 30 fps.
When shooting in low light, you need to either shoot at long exposures on a tripod or crank up the ISO if you want to shoot handheld. A group of researchers at the University of Illinois Urbana-Champaign and Intel are bringing the best of both worlds. They’ve trained AI to process low-light images so they’re much cleaner and more usable than grainy photos where ISO is too high. This tech could let you shoot at faster shutter speeds and lower ISO and still get with sharp, clear photos.