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 if we would 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.
This year’s Adobe MAX brought some interesting announcements and new apps. One of the new features introduced at the Sneaks event really caught our eye. It’s called Project About Face, an AI-powered tool that can detect if the image has been manipulated, It also shows where the manipulation has been applied and even helps you to revert back to the original, unaltered photo.
In some situations, Photoshop’s Magic Wand tool can save you a whole lot of time when making selections. This group of tools is getting an upgrade, and a very powerful one: meet Object Selection tool. It’s a powerful AI-powered solution that helps you make even complicated selections by a simple click-and-drag. In the video below, Meredith Payne Stotzner of Adobe will show you how it works, and I must say it looks pretty impressive.
Photoshop’s Content-Aware Fill is soon to get an upgrade, and Adobe has just launched a video to show off the latest improvements. The Content-Aware Fill is getting more intelligent and more powerful than before, allowing you to be not only more precise, but also much faster while cloning out unwanted elements.
ImageNet, one of the largest publicly accessible online databases of photos, is removing 600,000 images from its system. In other words, that’s as many as half of the 1.5 million images in its “person” categories. The decision came after an art project ImageNetRoulette revealed racist and gender bias that underlines ImageNet’s artificial intelligence.
We’ve already seen that AI-generated faces can look so realistic that it’s sometimes difficult to distinguish them from real ones. And if you want to put a fake headshot to use, Generated Photos lets you choose from 100,000 AI-generated faces. They’re all free for download and you can use them whichever way you want. What’s more, many of them look so good that it’s hard to tell them apart from photos licensed by stock photo companies.
If you have ever uploaded a photo to Facebook, you know that its image recognition tech automatically suggests tags of people. This feature was set to default, but Facebook announced yesterday that it will no longer offer tag suggestions when you upload a photo. In other words, its facial recognition will no longer be set to default.
Colorization and restoration of old photos is a painstaking and time-consuming process, especially if you’re working with heavily damaged images. Computer vision team of Mail.ru Group has introduced an AI-powered tool that will make his process simpler and easier. They’ve even launched a website where you can test it out and restore the vintage photos from your old family album. Or any other vintage photos, if you prefer.
From relighting images to removing backgrounds, the applications of AI tools in photography are many. The new AI-powered tool introduced by Chinese scientists can accurately fill in the blank spaces in all kinds of photos. Be it a front of a building, a landscape photo, even a portrait – the AI is trained to fill in the gap surprisingly accurately.