A team from the Massachusetts Institute of Technology (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) has designed a system called RePaint that uses artificial intelligence (AI) and 3D printing to reproduce paintings. The system is a workflow for spectral reproduction of paintings can capture the spectral color, regardless of light, and reproduce it. This technology could be used by museums to reproduce artwork that has been stolen or is on loan to another museum.
Despite the fact that the reproductions made by the researchers were only the size of a business card, the team noted that RePaint was four times more accurate than state-of-the-art physical models at creating the exact color shades for different artworks.
The researchers used a special technique called 'color-contoning' to get a full-color spectrum. 'Color-contoning' uses a 3D printer and 10 different transparent inks stacked in thin layers. The team then combined their new method with the traditional method of halftoning which uses small ink, in order to achieve a greater nuance of colors.
For the reproduction, the team trained a deep learning model to predict the most optimal stack of different inks and once the system learned that approach, the team fed images of paintings and used the model to determine what colors should be used in what particular areas for specific paintings.
Mike Foshey, a mechanical engineer at MIT CSAIL and co-author of the paper said that a system like RePaint could allow people greater access to rare pieces of art without having to risk harming the originals.
"We can picture RePaint being applied with restoration practice and education in museums so that greater numbers of people could be exposed to famous pieces of art beyond just the specific museums that house them," said Foshe.
Source: Forbes
ความคิดเห็น