In 2016, an earthquake reduced the Church of San Salvatore in Campi in central Italy mostly to rubble, destroying its 15th-century frescoes. What remained were fragments, a complex puzzle that conservators at the Ministry of Culture have been working to reassemble ever since.
But the pieces are few and far between, “isolated islands within vast areas of loss,” Serena Di Gaetano and Federica Giacomini, senior conservator-restorers at the ministry’s restoration institute, said in a joint emailed response to questions. Their work, they said, is to somehow “bridge the gaps between what remains and what has been irretrievably lost.”
Enter Alex Kachkine, 25, a graduate researcher in mechanical engineering at M.I.T. who improbably rocked the art world in June with a paper in the scientific journal Nature describing a new way to restore paintings with the help of artificial intelligence.
A hobbyist restorer, he wrote a program that analyzes damage and prints the fixes on a super thin mask. The mask can be laid over the painting, making it appear fully restored, but can also be removed to reveal the original. To create the mask, the program used over 55,000 hues in several hours, and worked about 65 times as fast as traditional restoration, Mr. Kachkine estimated.
The study was a side project, but it generated buzz among conservators around the world, including at the Ministry of Culture in Italy — to Mr. Kachkine’s surprise.
At his day job, he researches the electron beam sources that create the intricate circuitry on microchips, which are then placed into phones or other devices. “Those require very high degrees of precision,” he said. “And it turns out a lot of the techniques we use to achieve that level of precision are applicable to art restoration.”
Thank you for your patience while we verify access. If you are in Reader mode please exit and log into your Times account, or subscribe for all of The Times.
Thank you for your patience while we verify access.
Already a subscriber? Log in.
Want all of The Times? Subscribe.
The post The Hobbyist Restorer Who Rocked the Art World With an A.I. Innovation appeared first on New York Times.
