Fix damaged art in hours with AI
Jennifer Chu
created: Aug. 26, 2025, 9 p.m. | updated: Aug. 27, 2025, 2 p.m.
As a demonstration, he used the method to repair a highly damaged 15th-century oil painting he owned.
Next, Kachkine used software he developed to create a map of regions on the original painting that require infilling, along with the exact colors needed.
This map was then translated into a physical, two-layer mask printed onto polymer-based films.
Then he overlaid them by hand onto the original painting and adhered them with a thin spray of conventional varnish.
“There is a lot of damaged art in storage that might never be seen,” he says.
3 months, 3 weeks ago: MIT Technology Review