The Make3d algorithm, developed by Stanford computer scientists, can take any two-dimensional image and create a three-dimensional “fly around” model of its content, giving viewers access to the scene’s depth and a range of points of view, reports Physorg.

The algorithm breaks an image into tiny planes called “superpixels,” which are within the image and have uniform color, brightness and other attributes. By looking at a superpixel in context with its neighbors, analyzing changes such as gradations of texture, the algorithm makes a judgment about how far it is from the viewer and what its orientation in space is. Make3d can account for planes at any angle, not just horizontal or vertical. This allows it to create models for scenes that have planes at many orientations, such as the curved branches of trees or the slopes of mountains.

On the Make3d website, the algorithm puts images uploaded by users into a processing queue and sends an e-mail when the model has been rendered. Users can then vote on whether the model looks good, and can see an alternative rendering and even tinker with the model to fix what might not have been rendered correct the first time.

The software is best when used with landscapes and scenery rather than close-ups of individual objects. Future versions will introduce object recognition so that the software can recognize the human form in a photo to make more accurate distance judgments based on the size of the person in the photo.

To view the 3D images, you need to have Adobe Shockwave installed for Windows or VRML viewers for Windows/Linux. When viewing using Shockwave in the web browser, you can use keys on your keyboard to zoom in and out, move up and down or pan left and right of the images.

To view or create your own 3D objects, visit make3d.stanford.edu