Feb 21st 2014, 15:00, by Matthew Panzarino
We broke the news yesterday that Google was producing aprototype 3D sensing smartphone called Project Tango. We also broke down the capabilities of the vision processor inside the deviceand talked about what it means for the future of phones.
Now, we’ve got an exclusive look in the video below at a real 3D indoor map of a room captured with one of the prototype devices by Matterport. Matterport, which makes computer vision and perceptual computing solutions like software that maps and creates 3D reconstructions of indoor spaces, was one of the few partners Google chose to give an early prototype of the device to.
We spoke to Matterport CEO Bill Brown about the ability of Project Tango to recreate 3D scenes. Brown says that the project has accelerated the mobile 3D capture space significantly. Mobile devices have become viable capture platforms for 3D mapping far faster than most people following the tech expected it to happen.
Matterport’s pipeline of software allows it to capture both color camera data and a full mesh of 3D data at once, and reconstruct those together into an accurate model. Matterport has been building its own cameras to meet the quality and price point of what it needed‚ but Brown says that the Project Tango device is more than capable.
“We’re getting the same mesh quality that we’re getting from our camera,” says Brown. “It doesn’t ‘look’ as good, but that’s just because it’s a prototype.”
The look and feel of the model is slightly cruder because of the lower-resolution cameras on the Project Tango device, but Brown says that those things should be rectified soon enough.
As you can see by the model, the capabilities of the Project Tango device are already very impressive, and we’re only going to see our phones get more adept at sensing and interpreting our environment as time goes on.
Matterport will be appearing at Qualcomm’s keynote at the upcoming Mobile World Conference in Barcelona. It will be showing off its 3D capture and reconstruction software on mobile devices and talking more about what it does to help people run apps that utilize those models.