Augmented Reality (AR) is a neat tool that can be used for many different purposes, many of which are plain old fun, like this app that turns the ground to molten lava. Others are a little more serious, like this one that helps engineers.
However, a new usage of AR has just been designed by developer Cyril Diagne, and it's incredible. Diagne's tool shows how useful AR can be to snap and grab an image of a real-life object, and quickly and easily drag and drop it onto your desktop.
Gone are the days of fiddling, reshaping, and cutting images laboriously on Photoshop.
However exciting Diagne's new prospect may be, don't go grabbing your credit card quite yet as this is still in its research prototype phase. Regardless, it's quite safe to say that you'll quite likely see such an app or a tool on your devices in the near future, as it looks like a few companies are already developing software for similar tools, as per some of the responses on Diagne's Twitter video post.
This application of AR would certainly move it away from its current uses, which aren't mega practical for everyone: seeing what clothes, furniture, and makeup look like when they're pasted onto your face or into your home. These are useful for some, but not for all.
4/10 - Cut & paste your surroundings to Photoshop— Cyril Diagne (@cyrildiagne) May 3, 2020
Garment: SS17 by @thekarentopacio
Type: Sainte Colombe by @MinetYoann@ProductionType
Technical Insights: ↓#ML#AR#AI#AIUX#Adobe#Photoshoppic.twitter.com/LkTBe0t0rF
Moreover, this method of using AR would be an interesting switch. Instead of seeing how digital objects look like in your home, you can now take real-life objects and see what they would look like in a digital setting.
As Diagne explained in his Twitter video, there are two components to his AR tool. The first separates the foreground object from the background thanks to machine learning, and the second detects where your phone is pointing on your computer screen. It only takes 2.5 seconds to copy the object, and four seconds to paste it, but Diagne says he could speed that up.
Even though it's not yet available, Diagne's put his code up on GitHub for anyone who wants to have their hand at seeing if they can improve the demo even more. Have at it!