The new Disney Research algorithm is capable of turning 2D photos into 3D models.

Disney Research has developed an application that can build 3D models from ordinary photos. Thanks to the original algorithm, the program is able to build three-dimensional models of complex scenes straight from real life from several hundred images and therefore promises to be a useful tool for creating films, games and models for 3D printers.

Building a 3D model from several two-dimensional images that captured an object from different angles is no longer a novelty, but creating highly detailed environments in high resolution turned out to be difficult because of the need to process large amounts of data. The merit of Disney Research is that the algorithm they created is able to effectively manage such data scales, processing them without having to keep all the data in memory at the same time.

Now, many 3D-models are obtained by laser scanning. In the case of complex environments, one laser can simply not cope with the number of parts due to the fact that some objects will obscure others. The method of processing ordinary photographs makes it easier to "capture" the scene from several angles, but the construction of 3D-models of them, until recently, was very difficult.

The authors of the algorithm demonstrated its work on the complex scenes of external and internal spaces, which were recreated in 3D based on images taken with a 21-megapixel digital SLR camera. For comparison - before that, all reconstruction techniques were able to process only images with a resolution of 1-2 megapixels. To create each model took 100 shots.
')
The developers claim that the new approach can be applied to photographs taken with ordinary digital cameras.



The study is published in the report " Scene Reconstruction from High Spatio-Angular Resolution Light Fields ".

Source: www.3ders.org