Skip to Content

Soft Scissors for Cutting Photos

A new software tool from Microsoft Research lets people cut objects out of pictures and keep furry edges fuzzy.
August 17, 2007

Researchers at Microsoft have found a way to help photo editors cut a furry object out of a picture and keep its fuzz. As anyone who has used an editing tool like Photoshop knows, it’s impossible to easily and accurately cut around stray hairs or other soft edges. But Michael Cohen and his team at Microsoft Research have developed a tool, called Soft Scissors, that accounts for the basic shape of an object, such as a dog, as well as the shape of fur and stray hairs. (See slide show of images.)

Technology for making these soft cuts has been around for years, but there’s usually a trade-off between the quality of the cut and the amount of time it takes to process it. Cohen’s goal in this work, presented earlier this month at SIGGRAPH, is to reduce the amount of time it takes to produce a high-quality cut of a furry object.

The researchers modified an algorithm that they had previously developed for making high-quality cuts around difficult objects by adding three new characteristics to it. First, when a person traces around the object, the algorithm chooses a minimal amount of pixels to use to update the object’s edge. For instance, if most of the edge is smooth, then fewer pixels need to be collected to determine where the edge of the object is. Second, the color of the object is also incrementally estimated. Third, the width of the tracing tool automatically adjusts to accommodate longer stray hairs.

Currently, the algorithm requires a user to trace around an object, but the researchers suspect that it could also be used as the basis for a tool that automatically cuts furry foreground objects, possibly even in video.

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.