It isn't the first time that Bas' neural network reconstructions have been featured here on Bored Panda. His first post went viral, and the recreations in the second post were no less impressive than in the first one. We highly recommend checking them out, as even in today's post there are updated versions of the images that were in the older posts, and it's very interesting to see the evolution of how they were refined to what they are as of now.

Bas has been kind enough to share with us about his life and his passion in two separate interviews: "Although my career path has swayed in different directions, my focus has always been on playing with realism and illusion. Special effects, 3D animation, and video games all try to make fantasies plausible. Influenced by European comics, movies, and video games, I have experimented with most forms of visual storytelling."

"Working with classical art versus photography in neural networks for me feels like the next step in depicting ourselves. Just as photography changed the shape of classical painting, techniques based on artificial intelligence will start influencing and inspiring art and (post-)photography. AI applications are developing at an incredible speed and it will influence almost all segments of our society. I wouldn't be surprised if, in five or ten years, it will be possible to create moving, interactive three-dimensional characters with these techniques: super-realistic avatars that people are able to communicate within virtual surroundings."

"After working more than a decade in 3D animation, I was getting frustrated with the artificiality of it, so photography, for me, was a way to expand my horizons and investigation of what reality looks like: getting to know light and the way it behaves on materials, human faces, and how we perceive expressions in their smallest details."

"These 'Deep Learning' networks are trained with thousands of photographs of human faces and are able to create near-photorealistic people from scratch or fit uploaded faces in a 'Latent Space' of a total of everything the model has learned. I think the human face hasn't changed dramatically over thousands of years and apart from hairstyles and makeup, people that lived long ago probably looked very much like us, but we are used to seeing them in the often distorted styles of ancient art forms that existed long before the invention of photography."

But Bas isn't a one-trick pony: "Next to the historical recreations, I really love to work on completely made-up faces. For my audience, it sometimes is hard to see what they are looking at. Especially for people who are not familiar with the technical aspects of my work. That way, they don't know how much is made up. It could be a photograph of someone they have never seen before. I aim to make these faces interesting enough so they captivate and intrigue the viewer, like in any good classical portrait."