Microsoft Touts Imaging Technology

    August 8, 2007
    WebProNews Staff

Looks like Microsoft is hell-bent on making it impossible to tell what’s a real image and what’s been doctored, and is intent on making it so anybody with a digital camera can do so.

And that’s good news, really, for digital photographers, graphic designers, animation artists, web developers, and anybody that works with imaging.

It’s still in the research stage, so don’t expect the software in the immediate future. Right now it’s being shown off in San Diego to industry academic types.

What is it? It’s a few things, based on several papers presented in conjunction with several universities, including The Hong Kong University of Science and Technology and Carnegie Mellon.
Click for larger Image
One technology, presented in a paper called Image Deblurring with Blurred/Noisy Image Pairs, allows two blurred or noisy images of the same object to be transposed onto each other to form a detailed, clearer image. This comes in handy for not only transforming substandard photos into usable ones.

Another, described in Photo Clip Art, lets designers get around building graphics or animation from the ground up by allowing real images to be inserted in a real, 3D kind of way. 

The last one, called "Soft Scissors" allows for more precise cutting of difficult images involving fur or curly hair, which make it difficult to determine which is background and which is foreground.

All of the research will be presented at SIGGRAPH 2007 in San Diego this week.

The Image Deblurring research promises to make it easier, with off-the-shelf, hand-held cameras, reconstruct photos taken in challenging environments. Eventually, Microsoft will produce the software for this and the others.

“In this research, we presented an image deblurring approach to produce a high quality image by combining a blurred and noisy pair of images,” says Jian Sun, Microsoft Research Asia. “The result is that the reconstructed image is sharper than the blurred image, and clearer than the noisy one. Using a blurred/noisy image pair for input, we are able to obtain incredible image deblurring results that were hardly imaginable before.”

The technology discussed in Photo Clip Art, is being touted as one useful to animators and architects looking to make their work extra realistic.

“Our goal was to solve the grand challenge of computer graphics by creating realistic images for user-defined scenes,” says Carsten Rother, Microsoft Research Cambridge. “In contrast to graphics, which creates a three-dimensional world from scratch, we turned the problem upside-down by combining real images in such a way that we never break the realness of them.

"Instead of trying to manipulate the object to change factors such as its orientation and color distribution, we simply retrieve an object of a specified class that has all the required properties from our large object library."

And what’s probably a pretty neat development for designers that have had to cut images involving hair or fur, "Soft Scissors" aims to alleviate the inherent difficulties.

“In the past there were ways to move objects, but it required the user to draw a line around the object as if they were using a pair of scissors and then cut the objects out,” said Microsoft’s Michael Cohen. “That’s hard to do if the fuzzy boundary of the subject is a mix of background and foreground.

“The system looks ahead of the user’s actions to see how fuzzy the subject is and adjusts how soft the scissors are to come up with a much clearer image. It just does the right thing automatically. Users can select the new background ahead of time and then, as they’re brushing, see the edge of a dog for example going into a new background. Soft Scissors draws a soft line, a line that gradually and softly separates the foreground and background.”

And for anybody dealing with digital imagery, that sounds like a few nice developments.