You can’t go back in time to see how Monet or Van Gogh made their masterpieces, but AI might give you the next best thing. MIT CSAIL researchers have created a machine learning system, Timecraft, that can deduce how a painting was produced and recreate the likely brushstrokes, even for famous artists. The design was first trained on 200 timelapse videos of digital and watercolor paintings, after which the scientists produced a convolutional neural network to ‘deconstruct’ artwork based on what it had learned.
The results aren’t perfect, but they’re more effective than you might think. Timecraft was better than existing benchmark tests over 90 percent of the time. And when used to recreate paintings that already have timelapse videos, it fooled almost half of the people participating in an online survey.
The source code will be available if you’re willing and able to try it yourself, or to build upon the work. Apart from the virtual history lessons, this could be useful for illustrating general painting techniques to relative newcomers — say, starting from the background and working ‘closer’ to the viewer. It may be a long while before an AI becomes the next Bob Ross, but it’s not a far-fetched idea after this.
