A new research paper by Google researchers Hui Fang and Meng Zhang has outlined their attempt to teach Google’s AI how to take aesthetically pleasing photos.
Creatism: A deep-learning photographer capable of creating professional work are the researchers attempt to apply machine learning to the creative process.
The first step was to define different aesthetic aspects of photography like composition, saturation and detail. They then analyzed 15,000 high-ranking photo 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 to administer 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. [Source: Motherboard]
Of the 173 photos evaluated, 41% were ranked at or above a semi-pro level (3 or greater), and 13% of the photos scored at or above 3.5. In comparison, 45% of actual professional photos received a score of 3.5 or higher. [source]