CMU Algorithm Converts 2D Images to 3D

Posted 14 Jun 2006 at 22:51 UTC by steve Share This

A CMU press release claims researchers at the CMU Robotics Institute have developed an algorithm that can automatically convert conventional 2D images into 3D representations. The process, known as geometically coherent image interpretation, was developed by Alexei Efros, Martial Hebert, and graduate student Derek Hoiem. Computer vision expert Takeo Kanade had this to say: "The amazing thing they did was show that it was actually possible. I would say it's a breakthrough." For some technical details on their approach, see their new paper, Putting Objects in Perspective (PDF format).

See more of the latest robot news!

Recent blogs

22 Jan 2017 mwaibel (Master)
17 Jan 2017 shimniok (Journeyer)
3 Oct 2016 steve (Master)
27 Aug 2016 AI4U (Observer)
16 Aug 2016 Flanneltron (Journeyer)
9 Jul 2016 evilrobots (Observer)
27 Jun 2016 Petar.Kormushev (Master)
2 May 2016 motters (Master)
6 Nov 2015 wedesoft (Master)
10 Sep 2015 svo (Master)
Share this page