Microsoft Researchers Generate 3D Models From Ordinary Smartphones

New submitter subh_arya writes: Engineers from Microsoft Research have unveiled the first technology to perform 3D surface reconstruction from ordinary smartphone cameras. Their computational framework creates a connected 3D surface model by continuously registering RGB input to an incrementally built 3D model. Although the reconstruction results look promising, Microsoft does not plan to release an app anytime soon.

Comments

launching it soon

[Anonymous Coward]

Seems the submitter didn't read the article:

Currently, the app is not available for download - however the team is planning on launching it soon.

Re:this is old hat.

[subh_arya]

Its true that the concept of 3D reconstruction from dense stereo/structure from motion is not new. However, the computational pipeline integrated entirely into a mobile device without any expensive hardware or offloading computation on a cloud, differentiates this effort from the previous ones.

Re:123D Catch? Autodesk already has an app doing t

[Thagg]

The differences are significant:

1) The Microsoft app works in real-time on the phone, rather than 123D Catch processing in the cloud
2) The Microsoft app shows real-time results, so you can see where there are issues, and continue to photograph until they are resolved. With 123D Catch you patch errors in post.
3) The Autodesk 123D Catch app actually exists, and the earlier web-based version has been around for about four years.

I'm kind of surprised that Microsoft isn't using the acceleration and magnetic sensors in the phone to help determine the camera position. It's one of the features that phone cameras have that DSLR's don't.