Google Tango (https://www.google.com/atap/project-tango/) is able to do pretty impressive 3d reconstruction from what I hear. However it has a number of cameras, whilst linked technique can work with just one image (with enough training).

reconstructing depth from 2+ offset images is vastly simpler than from a single frame.

There's an OpenCV tutorial for those wishing to try it[0].

[0] http://docs.opencv.org/3.0-beta/doc/py_tutorials/py_calib3d/...

Yup, but I think there's a desire to get good 3d-reconstruction techniques for single images because in practice you often want to do reconstruction in extremely small environments where using multiple cameras is sometimes not feasible for various reasons.

Google Camera can already do this from a single camera. It takes a bunch of photos as you move the phone around a bit and reconstructs the depth from multiple shots.

http://googleresearch.blogspot.com/2014/04/lens-blur-in-new-...