Skip to Content

Microsoft Adds "Augmented Reality" to Bing Maps

At the TED conference this week, Microsoft announced a new, AR mapping feature.

Microsoft just added an interesting new feature to Bing Maps–augmented reality. Actually, it’s a bit more like augmented reality in reverse.

A new function, called Streetside Photos, takes real images and video clips and neatly stitches them onto the Bing Map’s street-level view, using a clever combination of geolocation information (from a GPS-enabled device, or added manually by the user) and imaging-matching algorithms. This means you can, for example, zoom in on a street and see an image of a particular storefront that was just uploaded to Flickr or Twitpic instead of the standard one. Steetside Photos, which is available for Seattle and San Francisco maps, also includes some nice historical imagery.

Blaise Agüera y Arcas, architect of Bing Maps, demoed the feature today at the TED conference, which is taking place in Long Beach and Palm Springs, California.

Agüera y Arcas presented another image-stitching program called Photosynth at TED in 2007. He tells me that the new application’s algorithms are similar to Photosynth’s but effectively work in reverse. “In Photosynth you start off with a bag of disorganized photos and it finds visual connections,” he says. “This is the same; instead of a bag of photos I have one and all of the structured imagery [to attach it to].”

The software behind Streetside Photos can adjust a photo so that it matches to within a few inches, rather than a few feet. This kind of precision is important for augmented reality to work effectively. “The pushpin or the GPS both have quite a bit of inaccuracy,” says Arcas. “It’s typical for it to be off by 40 meters or more. Some are even more ambiguous.”

The user sees a list of photos on the side of the screen and, if she clicks on one, the map view moves to that spot and the photo becomes a bubble overlaying it.

Perhaps most impressively, it can overlay moving video on top of a map, creating a “lens” type of effect, as illustrated in the video at Pike Place Market in Seattle below. While Agüera y Arcas would not say if there will be a Smart phone app to follow Streetside Photos, it seems like a natural progression.

Agüera y Arcas explain the concept in the video below.

Credit: Microsoft

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.