A team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has created a new AI system aimed at designing faithful reproductions of paintings. Called RePaint, the tool combines 3-D printing and deep learning to authentically recreate artworks.

And the process works regardless of different lighting conditions or placement. “If you just reproduce the color of a painting as it looks in the gallery, it might look different in your home,” said Changil Kim, one of the authors on a new paper about the system.

“Our system works under any lighting condition, which shows a far greater color reproduction capability than almost any other previous work.”

The researchers reproduced several oil paintings created by an artist collaborator and found RePaint to be more than four times more accurate than state-of-the-art physical models at creating exact color shades. Current productions are only about the size of a business card, due to the slow nature of printing, but the team hopes more advanced printers could make larger paintings more efficiently and speedily. 

“The value of fine art has rapidly increased in recent years, so there’s an increased tendency for it to be locked up in warehouses away from the public eye,” said Foshey. “We’re building the technology to reverse this trend, and to create inexpensive and accurate reproductions that can be enjoyed by all.”