MIT graduate student reduced painting restoration from 230 to 3.5 hours

MIT graduate student Alex Kachkin developed a cool method for painting restoration using artificial intelligence. Reducing work time from many months to several hours. As a demonstration, he restored a work by an unknown Dutch master of the 15th century that had seriously suffered from time.

The restoration process included several technological stages. First, algorithms created a digital copy, filling small cracks based on analysis of neighboring colors and restoring ornaments. To preserve historical authenticity, the researcher refused generative neural networks. Instead, he supplemented lost elements like faces with fragments from other works by the artist, using traditional graphic editors. The final step is truly genius. The restored digital elements were printed on ultra-thin transparent polymer and overlaid on the original. This film is invisible to the human eye but can be easily removed without the slightest harm to the painting. The entire application process took only 3.5 hours, while traditional restoration would require more than 230 hours of painstaking work. This technology will open access to many paintings around the world. Because it turns out that 70% of all museum paintings are not displayed. Due to damage.