AI 'resurrects' 54 Roman emperors, in stunningly lifelike images

A description of Caligula said the emperor had "a glare savage enough to torture."
A description of Caligula said the emperor had "a glare savage enough to torture." (Image credit: The Metropolitan Museum of Art/Reconstruction courtesy of Daniel Voshart)

Ancient Roman emperors' faces have been brought to life in digital reconstructions; the unnervingly realistic image project includes the Emperors Caligula, Nero and Hadrian, among others. 

The features of these long-dead rulers have been preserved in hundreds of sculptures, but even the most detailed carvings can't convey what these men truly looked like when they were alive. To explore that, Canadian cinematographer and virtual reality designer Daniel Voshart used machine learning — computer algorithms that learn through experience — in a neural network, a computing system processes information through hierarchies of nodes that communicate in a manner similar to neurons in a brain.

In the neural net, called Artbreeder, algorithms analyzed about 800 busts to model more realistic facial shapes, features, hair and skin, and to add vivid color. Voshart then fine-tuned Artbreeder's models using Photoshop, adding details gleaned from coins, artworks and written descriptions of the emperors from historical texts, to make the portraits really come to life.

Related: Photos: The reconstruction of a teen who lived 9,000 years ago

"There is a rule of thumb in computer programming called 'garbage in garbage out,' and it applies to Artbreeder," Voshart told Live Science in an email. "A well-lit, well-sculpted bust with little damage and standard face features is going to be quite easy to get a result." In contrast, a dataset including damaged sculptures or ones photographed under poor lighting can produce proverbial "garbage" images that aren't very realistic.

The busts that Voshart preferred to use as the primary sources were carved when their emperor subject was still alive, or were the most skillfully made, he said in a blog post

For skin color, Voshart would either provide Artbreeder with a colorized reference image, or let it "guess" how to distribute hues so that the surface of the model resembled realistic human skin. 

"I can change skin tone and change ethnicity somewhat with manual controls," he said.

Voshart fed Artbreeder a colorized model of the Roman emperor Philip the Arab, who ruled from A.D. 244 249, to help the neural net create a realistic skin color for the emperor's portrait. (Image credit: Courtesy of Daniel Voshart)

Tracking down all the art and reference text for the emperors took approximately two months, and assembling each portrait required about 15 to 16 hours on average, Voshart told Live Science.

For the emperor Caligula, who ruled from A.D. 37 to 41, Voshart adjusted the Artbreeder model using descriptions that included "head misshapen, eyes and temples sunken," and "eyes staring and with a glare savage enough to torture," from a paper titled "Personal Appearance in the Biography of the Roman Emperors," published in 1928 in the journal Studies in Philology

Nero, emperor from A.D. 54 to 68, had a more rounded jaw, skin that was "freckled and repulsive," and a face that was "agreeable rather than attractive," according to the 1928 paper.

Nero became emperor at the age of 17 after the death of his adopted father, the Emperor Claudius, in A.D. 54.  (Image credit: Courtesy of Daniel Voshart)

Related: The weird reason so many Roman emperors were assassinated

When Voshart began the Roman Emperor Project as a distraction during the COVID-19 quarantine, his knowledge of the ancient emperors was "close to zero," he said. Nevertheless, what started as a diverting art experiment intrigued Voshart enough to eventually include 54 emperors, spanning a period in the Roman Empire that is sometimes called the Principate, from 27 B.C. to A.D. 285, he wrote on his website.

Knowing little about his subjects was actually a plus, allowing him to shape their faces without preconceptions or bias, Voshart said.

"In a forensic reconstruction, for example, you only want relevant information about hair, skin, known scars," and other physical features, Voshart explained. "Knowing aspects of personality can unduly influence an artist," leading them to craft a portrait that reflects a skewed perception of the subject, he said.

You can see more of Voshart's reconstructions on his website, and a poster of the 54 faces in the Roman Emperor Project is available at his Etsy store.

Originally published on Live Science.

Mindy Weisberger
Live Science Contributor

Mindy Weisberger is an editor at Scholastic and a former Live Science channel editor and senior writer. She has reported on general science, covering climate change, paleontology, biology, and space. Mindy studied film at Columbia University; prior to Live Science she produced, wrote and directed media for the American Museum of Natural History in New York City. Her videos about dinosaurs, astrophysics, biodiversity and evolution appear in museums and science centers worldwide, earning awards such as the CINE Golden Eagle and the Communicator Award of Excellence. Her writing has also appeared in Scientific American, The Washington Post and How It Works Magazine.

  • OldKingSol
    They would look a lot better if they didn't keep the right half pixellated for some bizarre reason. Still, it's enough of a glimpse to appreciate it!
    Reply
  • Ebindog
    Nero looks like Ed Sheeran. Scary.
    Reply
  • jes nemo
    I've gotta say when I saw Nero was a ginger, history made sense.
    Reply
  • Wanda
    Ebindog said:
    Nero looks like Ed Sheeran. Scary.
    I think he looks a lot like Prince Harry, although Harry is way cuter.
    Reply
  • gsimonel
    Well, a random AI guess is about as good as a random human guess.
    I guess.
    Reply
  • Lucille
    Who in his right mind would be interested in how Caligula or Nero looked? The former was involved in weird sex and the latter was indeed a murderer. Neither one was worthy to look upon. But they both probably looked Italian.
    Reply