Skip to main content

Adobe and UC Berkeley team up to develop neural network image editor

Generative Visual Manipulation on the Natural Image Manifold
Machine learning is all the rage these days, and it could have a future in Photoshop. Adobe is working with researchers at UC Berkeley to develop software that uses artificial intelligence to help users realistically manipulate objects in an image with a few simple brush strokes.

Like the Neural Photo Editor project from researchers at the University of Edinburgh we covered earlier this week, the Adobe/Berkeley project uses adversarial networks to train the system to make realistic edits based on minimum user input. Three brush tools — coloring, sketching, and warping — allow for different aspects of the image to be manipulated. The demonstration video above shows how a user can simply paint a stroke of blue over a black shoe and the system automatically applies a blue shade to the entire shoe.

The warping tool allows for a user to alter the shape of the object in ways either subtle or extreme, while keeping it within the bounds of realism. In the video, it was used to make a shoe slimmer and change a handbag into a completely different shape. Fine details can be added with the sketching tool.

One of the tool’s most impressive features, however, is its ability to generate new images on the fly. A user simply draws an outline of a shape (in this case, another shoe) and the system generates images that fit the mold. But it can also generate full scenes: The presenter in the video created a mountain landscape painting with just a few brush strokes of different shapes and colors.

As the researchers explain in their paper, they envision this tool as speeding up workflows for image retouchers and opening up the world of image manipulation to people without advanced artistic skills, but it will likely be some time before this technology makes its way into an Adobe Creative Cloud update. As we’ve seen in AI-based image generators before, the resolution appears to be very limited. One day, however, maybe we’ll all be using this or a similar system to design our own sneakers from our laptops.

Editors' Recommendations

Daven Mathies
Former Digital Trends Contributor
Daven is a contributing writer to the photography section. He has been with Digital Trends since 2016 and has been writing…
Fujifilm’s successor to the wildly popular X100V has just landed
fujifilm unveils x100v successor x100vi

FUJIFILM X100VI Promotional Video/ FUJIFILM

Fujifilm has finally unveiled the successor to its super-popular X100V camera.

Read more
How to download Instagram photos for free
Instagram app running on the Samsung Galaxy Z Flip 5.

Instagram is amazing, and many of us use it as a record of our lives — uploading the best bits of our trips, adventures, and notable moments. But sometimes you can lose the original files of those moments, leaving the Instagram copy as the only available one . While you may be happy to leave it up there, it's a lot more convenient to have another version of it downloaded onto your phone or computer. While downloading directly from Instagram can be tricky, there are ways around it. Here are a few easy ways to download Instagram photos.

Read more
Astronaut captures stunning images of a snowy Grand Canyon
A snow-covered Grand Canyon seen from space.

In the final days of his six-month stint aboard the International Space Station (ISS), Danish astronaut Andreas Mogensen took some time out of his science work to snap some striking photos of a snow-covered Grand Canyon.

The images were captured from the station in recent days as it orbited Earth at an altitude of around 250 miles.

Read more