Team creates 3-D video from 2-D footage

Dec. 1, 2011
Researchers at ETH Zurich and Disney Research Zurich have developed a system that can automatically create high-quality stereoscopic video from monoscopic footage of field-based sports events. They claim that the 2-D to 3-D conversion method can be used to generate far-back field-based shots, which dominate viewing time in many sports.

While stereoscopic 3-D movies have been a hugely successful draw in theaters, 3-D televisions used in the home have only recently started to gain public attention.

One issue hampering their widespread adoption is that there is not a sufficient amount of suitable 3-D content available and few live broadcasts are able to be viewed in 3-D.

But all that might soon change, partly due to researchers like Lars Schnyder at ETH Zurich and Oliver Wang and Aljoscha Smolic at Disney Research Zurich (both of Zurich, Switzerland), who have developed a system that can automatically create high-quality stereoscopic video from monoscopic footage of field-based sports events.

They claim that the 2-D to 3-D conversion method can be used to generate far-back field-based shots, which dominate viewing time in many sports. For low-angle, closeup action, a small number of real 3-D cameras could be used in conjunction with the automated technique to provide full 3-D images of a sporting event.

The researchers say since their method creates results that are, in most cases, indistinguishable from real stereo footage, it could provide a means to reduce the cost of producing stereoscopic 3-D sports content for home viewing.

More information on the system is available.

-- By Dave Wilson, Senior Editor, Vision Systems Design

Voice Your Opinion

To join the conversation, and become an exclusive member of Vision Systems Design, create an account today!