Rembrandt painting restored with AI

The Rijksmuseum in Amsterdam has restored the missing edges of Rembrandt’s 1642 painting The Night Watch using artificial intelligence.

In 1715 the edges of the painting were cut off to be able to fit through doors at Amsterdam’s city hall.

The missing pieces have never been found, but a copy of the painting made before the corners were removed has given scientists working on the restoration an idea about what the original version would have looked like.

The museum said that it has had artificial neural networks working on reconstructing the original appearance of the painting.

After 300 years, the painting has finally been restored.

“Our attempt here is to make a best guess, without the hand of an artist, into what The Night Watch looked like,” said Robert Erdmann, senior scientist at the Rijksmuseum.

Images of what the painting should have looked have been mounted at the sides of the original piece. Museum visitors can now see three figures on the left-hand side of the painting, a helmet on the right, a clearer view of a boy in the left foreground, running away from the militia, and changes to The Night Watch’s composition.

‘Operation Night Watch’ has collected a huge amount of data – around 51 terabytes – from all the different imaging techniques used to study the painting.

For some techniques the museum collected lots of information for each pixel, even though it had comparatively fewer pixels. For example for MA-XRF scanning, 4096 channels of information per pixel were analysed by a computer to produce a map of a few dozen elements.

    Share Story:

Recent Stories


Bringing Teams to the table – Adding value by integrating Microsoft Teams with business applications
A decade ago, the idea of digital collaboration started and ended with sending documents over email. Some organisations would have portals for sharing content or simplistic IM apps, but the ways that we communicated online were still largely primitive.

Automating CX: How are businesses using AI to meet customer expectations?
Virtual agents are set to supplant the traditional chatbot and their use cases are evolving at pace, with many organisations deploying new AI technologies to meet rising customer demand for self-service and real-time interactions.