GOOGLE'S AI IS TEACHING ITSELF PHOTOGRAPHY!

Google's AI takes better pictures than we will ever do if we get to go travel the world like the gallery above. A new research paper by Google researchers Hui Fang and Meng Zhang has outlined their attempt to teach Google's Artificial Intelligence how to take aesthetically pleasing photos. 

The first step to teach the AI was to define different aesthetic aspects of photography like compositions, saturation and detail. They then analysed 15,00 high-ranking photos thumbnails from 500px.com so the neural network could begin to understand which cropping and lighting effects were the most popular.

The next step was to unleash the machine on Google Street View and let it take snapshots of scenic locations and crop and light the results accordingly.

The final step was set a “Turing-test”-like experiment, to objectively measure the quality of its creations. To do this the researchers asked six professional photographers—all of whom had at least a bachelor’s degree in photography and two years of professional photo experience—to independently evaluate the photos.

Each photo was ranked 1-4, where 1 indicated a beginner-level photo with little artistic merit and 4 indicated a professional photo. None of the photographers knew that any of the photos had been generated by a machine. 

You can find all 256 photos and the original Google Map Street View locations on GitHub. You can read “Creatism: A deep-learning photographer capable of creating professional work” at arXiv.org.