Skip to Content
Uncategorized

This Pocket AI Is Fast Enough to Retouch Smartphone Pics Before You Snap Them

August 2, 2017

Awful photographers could catch a break thanks to a new AI that improves images before they’re even captured. A collaboration between researchers from Google and MIT’s Computer Science and Artificial Intelligence Laboratory, the new software uses an neural network that was trained on a set of 5,000 images, each of which was retouched by five different photographers. It uses the knowledge gained from studying those pictures to tweak colors and contrast to make the image look better. The example above shows a raw image on the left and the AI’s retouched version on the right.


But what’s impressive here isn’t the fact that an AI can retouch a photo nicely. Nope: it’s the fact that the neural network required to do it has been made so efficient that it shows the user its results in real-time, in the viewfinder of their smartphone camera. That’s achieved by having the algorithm work on a low-resolution version of the image, then making the neural net create a set of equations that are applied to enhance the image rather than doing it pixel-by-pixel. (There are more details about how it works in this paper.)


Lightweight pocket AIs like this are becoming more popular with smartphone makers like Apple, who want to work out ways to use the smarts of AI without draining batteries or providing users with laggy experiences. Expect to see more advances like it in the near future.

 

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.