NPR logo Obstructions Vanish From Images Treated With New Software From MIT, Google

America

Obstructions Vanish From Images Treated With New Software From MIT, Google

Researchers from MIT and Google used a video to explain how their new algorithm separates background and foreground scenes from images. i

Researchers from MIT and Google used a video to explain how their new algorithm separates background and foreground scenes from images. YouTube hide caption

toggle caption YouTube
Researchers from MIT and Google used a video to explain how their new algorithm separates background and foreground scenes from images.

Researchers from MIT and Google used a video to explain how their new algorithm separates background and foreground scenes from images.

YouTube

In a mesmerizing video, a researcher explains the math behind what seems like magic — photographs in which the view is obscured by things like chain-link fences and reflections become free of clutter with just a few clicks.

Researchers at MIT and Google have created an algorithm that uses multiple images taken from different angles to separate foreground obstacles from the subject that's in the background — anything from your favorite view or a sign in a window on a bright day.

We don't entirely understand how they do this, and there's no word yet on when the software might reach consumers, but it's a pretty neat trick. Check it out:

Tianfan Xue YouTube

Comments

 

Please keep your community civil. All comments must follow the NPR.org Community rules and terms of use, and will be moderated prior to posting. NPR reserves the right to use the comments we receive, in whole or in part, and to use the commenter's name and location, in any medium. See also the Terms of Use, Privacy Policy and Community FAQ.