Inserting your virtual copy in a game

French researchers have developed a new system to enable users to insert virtual copies of themselves into video games or on the Web. This system combines high performance video acquisition, computation and graphics rendering. It was introduced last week at SIGGRAPH 2007. This system is called GrImage (for 'grid' and 'image') -- a French word which also means 'make-up' for actors -- a pretty bad choice in my opinion. Anyway, it could be used to control your realistic avatars not only in games, but also in video conferences. But read more...

French researchers have developed a new system to enable users to insert virtual copies of themselves into video games or on the Web. This system combines high performance video acquisition, computation and graphics rendering. It was introduced last week at SIGGRAPH 2007. This system is called GrImage (for 'grid' and 'image') -- a French word which also means 'make-up' for actors -- a pretty bad choice in my opinion. Anyway, it could be used to control your realistic avatars not only in games, but also in video conferences. But read more...

The GrImage acquisition platform

You can see above the GrImage acquisition platform with all its video cameras (Credit: GrImage project, INRIA). Here is a link to a larger version of this picture. And here are other links to the GrImage Home Page and a photo and video gallery.

Before going further, let me say I'm intrigued by the article I'm using for this post. Is it Life Style Extra which really found the story? It seems that this site used excerpts of an article of New Scientist, "Your virtual avatar has all your best moves" (Matthew Busse, New Scientist Magazine Issue 2617, August 16, 2007) without 'really' mentioning its sources. But you can see the beginning of the New Scientist on its website and the full article on TMC.net to make your mind.

Now, let's look at how the system works. "Most existing methods of motion capture require a person to don high-visibility markers enabling the relative position and movement of different body parts to be recorded by video camera in 2D and easily rendered. The INRIA team wanted to do away with the markers. Instead they used between six and 14 video cameras to capture the person from multiple angles and created software that identifies and extracts their silhouettes and combines them to form a rough 3D model. The software quickly adds colour and texture to the model, resulting in a fleshed-out avatar that mimics the subject's movements in real time."

GrImage was on display last week at SIGGRAPH 2007 in a session about Emerging Technologies. Here is a link to Grimage at SIGGRAPH 2007. "Visitors could stick their hands in a "recording space" lined with cameras and play with a virtual jack-in-the-box as well as some soft, squishy objects."

For more information about this project, you can look at this list of publications by the research team. In particular, you should read "The GrImage Platform: A Mixed Reality Environment for Interactions" (PDF format, 7 pages, 486 KB), a technical paper which was presented at the 2006 International Conference on Vision Systems, New York, (ICVS'2006).

Sources: Life Style Extra, UK, August 16, 2007; and various websites

You'll find related stories by following the links below.