14 DAY TRIAL // Microsoft Research has developed a brand new technology that would allow users to digitally fix the way their hair looked in some photos, all based on a 3D modeling technique that takes care of the whole process.
Basically, users are only required to draw a few strands around the areas they’d like to fix and let the application do the rest of the job. As expected, the system analyzes the photo and fills out the strands using realistic-looking hair, matching the one in the picture.
Lvdi Wang, associate researcher at the Internet Graphics Group in Microsoft Research Asia, will present the technology at SIGGRAPH 2013 as part of the “Dynamic Hair Manipulation in Images and Videos” keynote.
“We proposed a new method for creating a 3-D hair model from just one single photograph or short video,” Wang explains.
“Such a model contains tens of thousands of individual hair strands and allows the user to manipulate hair in images or videos in a structure-preserving and semantically meaningful way.”
The whole process shouldn’t take more than just a few seconds, so Microsoft promises that in case it gets the green light, the technology will be easily accessible for any user category, including absolute beginners.
At the same time, such an app can be always used to render a virtual haircut, again, with only a few clicks in a specific picture.
“To get the correct hair-editing results we must make sure the 3-D hair strands are indeed grown from the scalp of a 3-D hair model, so that when the user moves the head or combs the hair, the hair roots are always fixed on the scalp,” Wang explains.
Microsoft claims that its engineers have been working on this tech for the last year and a half, so this new digital hair manipulation system could really see daylight at some point.