YouTube’s Using Machine Learning to Improve the Look of Your Shorts Clips

Your YouTube Shorts may get a polish after posting, as part of a new experiment to clean up the Shorts feed.

YouTube has confirmed that it’s running a new test which aims to improve the look of YouTube Shorts clips, in order to make them appear more crisp, by using machine learning techniques to refine playback.

As explained by YouTube Liaison Rene Ritchie:

“We’re running an experiment on select YouTube Shorts that uses traditional machine learning technology to unblur, denoise, and improve clarity in videos during processing, similar to what a modern smartphone does when you record a video. YouTube is always working on ways to provide the best video quality and experience possible, and will continue to take creator and viewer feedback into consideration as we iterate and improve on these features.”

So YouTube’s trying to make your Shorts look better, even if you’re not an expert camera person.

Which could be good, I guess, in ensuring a better user experience, while also making your content look cleaner and more detailed in the Shorts feed.

But then again, some users have raised concerns that YouTube’s upscaling process is making Shorts look more AI-generated, which could blur the lines between real, human-captured content and AI slop.

And that could end up turning your audience away, though as YouTube notes, it’s not using AI to revise or change your Shorts clips, as such, it’s only applying “traditional” machine learning processes, which only aim to sharpen and improve the presentation of clips.

What the impact of that will actually be is impossible to say, but if you notice that your Shorts look a little different when they go live, this could be why.

YouTube says this is only a small-scale experiment for now, with the intention of improving the Shorts experience for all viewers.