Although there are filters (滤镜) which can change digital photographs to make them similar to a painting, obvious differences still exist.
A brandnew painting AI has been made public recently. Much like the pupils of the old masters, the new AI studies the work of great painters like Vermeer and Van Gogh and learns to reproduce their works.
The AI, named "PaintBot"， is the creation of a team of researchers from the University of Maryland, the Bytedance AI Lab and Adobe Research.
PaintBot can not only reproduce the work of different artists but create new works based on photographs in the chosen painter's characteristic style.
To train the AI to imitate (模仿) a given artist's technique, the researchers would present it with between 3 and 10 reference paintings. With each reference painting it studies, the AI gradually learns to recognize the various characteristics of the given artist's technique, including the stroke (笔画) color, position and size—along with the order in which each brushstroke should be made.
PaintBot uses a technique known as reinforcement learning (强化学习). During the learning process, the AI would practice reproducing reference paintings, which it would then compare with the original work to see how similar the two were and if it was improving its imitation of the artist's style. It takes around six hours for the AI to learn to imitate a given painter.
Once the AI has mastered a particular artist's technique, the researchers could present it with a new image to reproduce in the same style. The AI then uses what it has learnt to produce a new painting, putting down each brushstroke one at a time.
After being trained in a given style, PaintBot takes only around five minutes to produce each of its digital masterpieces.
The way that PaintBot's compositions are built up from thousands of individual brushstrokes makes the AI's works more realistic than those online filters.
