Subscribe to Here’s the Deal, our politics newsletter for analysis you won’t find anywhere else.
Thank you. Please check your inbox to confirm.
Leave your feedback
After analyzing thousands of webcam snapshots of landscapes in various weather conditions, computer scientists at Brown University have developed a system that can automatically change the appearance of weather in nearly any outdoor photo.
With this new tool, a user provides an image, left, and can chose different weather attributes for which to apply to the photo. Photo by Brown University.
The team’s algorithm adjusts 40 different attributes in photos that the researchers determined are connected to our perception of weather. The resulting software can easily alter a lush green landscape to make it appear covered in snow or subjected to drought.
“Programs 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’d manipulate text.” said James Hays, Manning Assistant Professor of Computer Science at Brown.
To identify the attributes that enable us to identify weather in photos, the scientists commissioned Amazon’s Mechanical Turk crowdsourcing engine to rate photos based on perceptual and subjective qualities. Does a certain photo show a sunset or a sunrise? Is it gloomy or clear? You can explore an interactive version of the team’s data set at their project website, or use weather attributes to search the catalog of images that went into the development of the algorithm.
The software will be presented in a paper at next week’s SIGRAPH 2014, an international conference on interactive and computer graphics.
Travis Daub is Director of Digital at PBS NewsHour.
Support Provided By:
Additional Support Provided By: