Photography website PetaPixel reports that researchers affiliated with Google and MIT have devised an algorithm that automatically removes reflections and obstructions from photographs, provided multiple frames are captured. Even more intriguing: this algorithm can also recover a reflected image.
Differences between the reflections/obstructions and the scene can be detected and extracted by comparing all the different shots, resulting in one clear photo of the obstruction-free background scene, and one clear photo of the extracted obstruction (e.g. a reflection or fence).
Now that's where things get even crazier: the algorithm is able to provide clear photos of what reflections show....
The MIT Technology Review provides more details about the algorithm:
Michael Rubinstein, a research scientist at Google who worked as a postdoctoral researcher at Microsoft Research while some of the work was conducted, says the basic principle behind the algorithm is the phenomenon of motion parallax....
Tianfan Xue, lead author of the paper and a graduate student at MIT, says that in addition to reflections on windows and chain-link fences, the algorithm can correct for a number of different kinds of obstructions on windows like raindrops or dirt.
Fairly impressive! Does this have the potential to become a new standard tool for photographers, or will this appeal primarily to cameraphone-toting consumers?
(Score: 3, Interesting) by Hyperturtle on Thursday August 06 2015, @04:42PM
I am going to guess it'll be good for inserting clear and not obviously faked photographic evidence where it isn't supposed to be. See, we have you on camera, son, on that very day.
I have come to greatly distrust these inventions. I first learned to treat similar great inventions in photography with skepticism from A) watching the movie Running Man, and B) seeing the magazine cover that depicted Tanya Harding skating next to Nancy Kerrigan, when no such event had happened. It was one of the first (aside from novelty) use of directly fake and unabashedly fraudulent marketing to drive sales -- now they drive clicks, I suppose.
Seeing is believing, and if you control what is seen you can deliver the message you want.