Computer-generated human faces usually look plastic and unconvincing on the silver screen; one of the biggest problems is getting simulated light to bounce off the skin just right. Now computer scientists Henrik Wann Jensen of the University of California, San Diego, and Pat Hanrahan of Stanford University have written software that renders virtual skin in a more realistic way. A graphic artist defines the shape and color of the face, the lighting conditions, and the translucency of the skin; the software then uses physics to calculate how light is absorbed and scattered beneath the surface of the simulated skin. That gives the skin a softer, more diffuse, and more natural look than previous computer models did. What’s more, the technique requires no more time to render each frame of animation than existing methods, thanks to mathematical shortcuts. Studios and effects companies including Pixar, ILM, and Disney are starting to use the technique, says Jensen.
These weird virtual creatures evolve their bodies to solve problems
They show how intelligence and body plans are closely linked—and could unlock AI for robots.
A horrifying new AI app swaps women into porn videos with a click
Deepfake researchers have long feared the day this would arrive.
Chinese hackers disguised themselves as Iran to target Israel
But they left a few clues that gave them away.
DeepMind says it will release the structure of every protein known to science
The company has already used its protein-folding AI, AlphaFold, to generate structures for the human proteome, as well as yeast, fruit flies, mice, and more.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.