Free Library Converts 2D Image to 3D
Written by Mike James   
Wednesday, 10 October 2012

Microsoft Research has been hard at work doing impossible things again. This time it's a library of code that converts a 2D video or still image into a 3D depth image.

This is all about taking a simple 2D image and working out how far away from you each of the objects in it are. The algorithm attempts to construct a depth map of the sort the Kinect creates but without using a Kinect.

Once you have a depth map you can apply it to the single image and create a stereo pair which can be viewed as a stereoscopic image.

You might at first think that all of  this is an impossible task because you need stereo vision and hence a pair of stereo photos to work out depth. After all, we have two eyes to be able to judge depth. However, try looking at a scene with one eye closed you will still be able to judge distances and even more impressive, you can judge distances in a single photo.

 

3dphotos121

Single frames converted to depth maps - darker is closer

 

So how is this achieved?

The new software does the job by keeping a database of objects with known depths that it can recognize in the photo. It then estimates warping functions, which indicate how the object is different in the target photo. The matched object is assumed to be at the same depth as the library object. A label based smoothing procedure is then used to improve the depth estimates. If the input is a video then motion flow is used to improve the depth estimates - basically pixels that are in motion have to be in front of background pixels.

 

3dsamplecollection

The method was trained and tested using a set of videos that were gathered in stereo using a Kinect to measure depth where possible. You can see the arrangement used in the photo above.

You can see the algorithm in action in the following video:

 

 

From video to depth map to 3D stereo images

3dtoprunner

3dbottomrunner


You can download both the Matlab implementation of the algorithm and the training data.

More Information

Depth Extraction from Video Using Non-Parametric Sampling

Download source code

 

Related Articles

Halide - New Language For Image Processing

Super Seeing - Eulerian Magnification

Predator better than Kinect?

3D Input Using Just Projector & Camera

 

espbook

 

Comments




or email your comment to: comments@i-programmer.info

 

To be informed about new articles on I Programmer, install the I Programmer Toolbar, subscribe to the RSS feed, follow us on, Twitter, Facebook, Google+ or Linkedin,  or sign up for our weekly newsletter.

 

Banner


Firefox 1.0 Released 20 Years Ago
10/11/2024

A news item with the headline "Firefox browser takes on Microsoft" from 20 years ago has attracted renewed attention. It was originally published on the BBC News website on November 9th, 2004 rec [ ... ]



Microsoft Introduces Vector Abstractions Library For .NET
21/11/2024

Microsoft has announced a preview release of the Microsoft Extensions VectorData Abstractions library, which can be used to help integrate vector stores into .NET applications and libraries.


More News

 

Last Updated ( Wednesday, 10 October 2012 )