University of Washington (UV) researchers have developed a new software called Dreambit that lets a person predict what they would look as they age, get a different a hairstyle or move to a different country.
The computer vision researcher allows you to alter your looks without physically trying it by simply querying in your demand in an image search engine.
After uploading an input photo, you type in a search term — such as “India,” “permed hair” or “2021.” The software’s algorithms mine Internet photo collections for similar images in that category and seamlessly map the person’s face on the results.
The new software,which can also help show what missing people or criminals would look like disguised or at a later age, will be showcased at SIGGRAPH 2016, the world’s largest annual conference on computer graphics and interactive techniques and will be publicly available later this year.
Dreambit draws on previous research by Ira Kemelmacher-Shlizerman, assistant professorof computer science and engineering, and her team in combining algorithms in facial processing, recognition, three-dimensional reconstruction and age progression to create the blended images.
The software can also be used to imagine how a certain actor or actress will appear in a role. For example, the system can marry internet photographs of the actress Cate Blanchett and Bob Dylan to predict how she would appear playing the Dylan role in the movie “I’m Not There.”
The software system analyses the input photo and searches for a subset of internet photographs that fall into the desired category but also match the original photo’s face shape, pose and expression.
“The key idea is to find a doppelgänger set — people who look similar enough to you that you can copy certain elements of their appearance,” said Kemelmacher-Shlizerman. “And because the system has hundreds of thousands of photos to choose from, the matching results are spellbinding.”