With a new computer algorithm developed by researchers at Brown University in the US, a picture taken in July can be made to look a bit more like in January simply by typing "more winter".
The algorithm can edit photos according to 40 commonly changing outdoor attributes, the researchers said.
"Programmes like Photoshop are really powerful, but you basically need to be an artist to use them. We want anybody to be able to manipulate photographs as easily as you would manipulate text," said James Hays, an assistant professor of computer science at Brown University.
The new algorithm uses machine learning to make all the subtle changes in colour and contrast that happen across the entire photo -- changes that would normally require a skilled photo editor to fully replicate.
To start the project, the researchers defined a list of transient attributes that users might want to edit.
To teach the algorithm what these attributes look like, the researchers compiled a database consisting of thousands of photos taken by 101 stationary webcams around the world.
Armed with the knowledge of what each attribute looks like, the algorithm can apply that knowledge to new photos.
"If you wanted to make a picture rainier, the computer would know that parts of the picture that look like sky need to become greyer and flatter," Hays explained.
A paper describing the work will be presented this week at SIGGRAPH, the world's premier computer graphics conference to be held in Canada.
Comments
Hi! My name is Angie for short!
Add new comment