MIT's New System Converts 2D Video Of Soccer Games Into 3D Automatically

A wide spread adoption of 3D stereoscopic television is hindered by the lack of high-quality 3D content. One promising solution to address this need is to use automated 2D-to-3D conversion. However, current conversion methods produce low-quality results that exhibit artifacts that are not acceptable to many viewers. By exploiting the graphics-rendering software that powers sports video games, researchers at MIT and the Qatar Computing Research Institute (QCRI) have developed a system that automatically converts 2-D video of soccer games into 3-D. The converted video can be played back over any 3-D device - a commercial 3-D TV, or Google's new Cardboard system, which turns smartphones into 3-D displays, or special-purpose displays such as Oculus Rift.

Stereoscopic 3D (S3D) movies are becoming popular with most of big productions being released in this format. However, in practice, most movies are shot in 2D and then they are upconverted to S3D by manually painting depth maps and rendering corresponding views. This process yields very good results but it is extremely costly and time-consuming. Stereoscopic 3D production of live events is much harder. Manual upconversion is not possible. Shooting live events, such as soccer games, directly in stereo requires placing multiple stereo rigs in the stadium. This is challenging and it is rarely being attempted. Therefore, a high-quality, automated 2D-to-3D conversion method is highly desired for live events.