Researchers at the University of Washington have developed a deep learning method that only needs a single photo to make a believable video. If you have a photo of a waterfall, a river, smoke, or clouds, it predicts the previous and the next frame and creates a pretty cool animation.
There are now two ways of creating digital images with a camera. You can either follow a software-centric computational photography approach. The other way is to stick to traditional hardware-centric optical photography. The former is used with AI to help enhance the final image, the latter relies on the quality of the camera’s components (e.g. lens, sensor). The two techniques may differ, but they are not at all on a collision course. They can complement each other and even address each technique’s limitations.
The Instagram algorithm is something many of us love to hate. It’s an invisible entity we’ve been trying to beat over and over again to make our content more visible. But the truth is – none of us really know how exactly the algorithm works. Well, the company has finally decided to become more transparent about it and tell us more about how Instagram picks content for its users.
If you’ve ever wanted to work for Google, now’s your chance. Well, sort of. Google Photos is now expanding its survey that helps the algorithm recognize what’s in the photos. In other words, you’ll be able to label your images from scratch and tag them in order to train Google’s algorithm further.
Artificial intelligence keeps getting better. A group of scientists from China has developed an algorithm that can turn sketches into realistic portraits. It even works with pretty rough sketches, and the end results look very close to real photos of people.
We’ve already seen some AI software that can upsample low-res images. You know, CSI-style. Face Depixelizer is another AI-powered software, particularly focused on faces. It can take a pixelated, low-res photo and turn it into a realistic portrait. While the results are pretty impressive – the app doesn’t come without its quirks.
Instagram has introduced a new feature that could give us a glimpse of why we see some accounts in our feed more and some less often. Introduced on Thursday, the feature lets you see which accounts are shown in your Feed the most, and with which accounts you’ve had the least interaction.
Oceanographer and engineer Derya Akkaynak from MIT has developed an algorithm that “removes water” from underwater images. As a result, it makes the underwater world look exactly as it would if we were to see it on dry land. And it’s not only useful for scientists. For us “common folks,” it’s amazing to see the underwater world in a completely new context.
A group of MIT researchers has come up with a way to recover lost details from your blurry images and even videos. They have developed an algorithm that recognizes and automatically recovers blurred parts in your videos and stills.