Microsoft Research Aims To Automate Gif Creation

Microsoft Research has had a long history of looking at bringing static images to life.  A few months back MSR released an app called BLINK for WP8 and recently Cliplets for Windows 8.  Cliplets reanimates a portion of a scene based on user-specified regions and time intervals. The emphasis is on creative control—creating contrasting juxtapositions of frozen and dynamic content.  Think of the dynamic (animated) images in the newspapers shown in the Harry Potter films.  Or the Nokia Cinemagraph the app, same basic concept.  All these apps output .gif files.

With today’s mobile devices, users can find shooting high-definition video as easy as snapping a photograph. That should mean, before long, that preserving and sharing bursts of video might become as commonplace as the current practice of exchanging still images.  The MSR research project aims to captures a spectrum of looping videos with varying levels of dynamism, ranging from a static image to a highly animated loop.

The research is detailed in a technical paper, written by Zicheng Liao of the University of Illinois at Urbana-Champaign and Neel Joshi and Hugues Hoppe of Microsoft Research Redmond, titled Automated Video Looping with Progressive Dynamism.

“We have developed a technique to automatically create an infinitely looping video from a short input video sequence of five to 10 seconds,” explains Hoppe. “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.  In contrast, ‘automated video looping’ requires no user input. It tries to incorporate as much dynamic content as possible, so it is able to capture more scene activity, including subtle motions like water ripples and swaying grass.”

The automated solution offered by Liao, Joshi, and Hoppe enables each pixel to determine its own looping period.

“What is unique over prior work is that in the looping video, regions of pixels can have different looping periods, and these periods are found automatically as part of an optimization algorithm,” says Hoppe.  The second contribution of the paper is to show that once we have created the ‘most dynamic video loop,’ we can use information from the optimization to provide the user with simple controls over dynamism in the resulting scene,” says Hoppe.  “One such control is a slider that lets the user adjust the overall level of dynamism. 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.” “As dynamism, varies, it is necessary that small regions of pixels start or stop looping together,” Hoppe says. “For example, if only half of a branch was moving, we would see an obvious spatial discontinuity. We identify these ‘independent looping regions,’ again automatically, and let the user spatially adjust dynamism at the granularity of these regions.”

MSR colleague Johannes Kopf, stated “It would be very tedious for a user to manually identify all these small regions and their natural loops.

The researchers also have ensured that all regions of a scene loop well together. That segmentation gives users the interactive ability to adjust the dynamism of the scene. The level of dynamic activity in the scene can depend on the user’s personal taste or mood.

To put it more simply, imagine doing something as simple as taking a ‘picture’ on your windows phone of a waterfall, and that picture automatically turning into a 5-second looped gif.  Going from a static to a more dynamic image.  I think we’ll see this research turned into a product sooner than later.

Source: Inside Microsoft Research