Skip to Content
Uncategorized

The Future of Faces

These days, everyone from Microsoft to ILM to Electronic Arts is trying to make computer-generated human faces look more realistic. But Clive Thompson, writing in Slate, argues that video-game developers should aim to make characters less realistic, not more. As…

These days, everyone from Microsoft to ILM to Electronic Arts is trying to make computer-generated human faces look more realistic. But Clive Thompson, writing in Slate, argues that video-game developers should aim to make characters less realistic, not more. As digital faces get closer to photorealism, he says, they look creepier and creepier–and less engaging.

I agree with the creepy part. Most CG faces lack the soft wrinkles and subtle expressions of the real thing, so they don’t look alive. But that’s with today’s technology. In five years, game graphics will be where movies are today. You’ll be able to interact in real time with characters as compelling as Gollum and 100 Agent Smiths. (These movie characters look good because they are based on real footage of real actors, processed by immense computers.)

Depending on whom you ask, researchers have already done 80 to 99 percent of the work necessary to make CG humans indistinguishable from real ones. Only that last bit remains. So what are we afraid of? That they’ll never get there–or that they will?

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.