Microsoft Research is offering up 19 project papers at this week's SIGGRAPH 2013 conference, including one on embedding code inside 3D printed objects. Yet another paper that is being brought to SIGGRAPH describes a project that could lead to a new way of creating short videos.
The Microsoft Research blog summarizes the paper,"Automated Video Looping with Progressive Dynamism" which the research team at Redmond co-authored with a team from the University of Illinois at Urbana-Champaign. According to Microsoft Research team member Hugues Hoppe:
We have developed a technique to automatically create an infinitely looping video from a short input video sequence of five to 10 seconds ... One can shoot a five-second video of a pretty landscape and generate an animated version of the scene to play on a PC desktop or in a slide show.
The project is an extension of Microsoft's previous work on Cliplets, which adds animation to still images, that Microsoft launched in March 2012. This new animated video loop technique will require no input from the user, with each video pixel determining its own looping period thanks to an optimization algorithm that's been created by the team.
After the video loop has been made, the user can access simple controls, such as a slider, to determine how much animation he or she wants to see in the clip. Hoop says:
In essence, we are traversing a sequence of video loops, from completely static to most dynamic. The clever part is that we don't actually have to store all these various loops. We just store the most dynamic loop, together with an ‘activation' value per pixel that indicates when that pixel should ‘turn on'--become dynamic—as the slider moves.
While there is no guarantee that this new short video looping program will be made available in the real world, we would not be surprised to see it pop up as part of a Windows 8 or Windows Phone 8 app at some point in the future.
Source: Microsoft | Image via Microsoft