Animating a person’s movements for a movie or video game can be costly and time consuming, requiring that actors be filmed with special cameras for every step and shrug. A new tool created by Zoran Popovic at the University of Washington and Aaron Hertzmann at the University of Toronto, however, can extrapolate a person’s movements from a single sequence of motions. First, the sequence is used to train the system. Then the animator picks a new movement for the digital character by, say, changing the position of its hands and feet. The system then calculates the most probable corresponding positions of the rest of the body. Popovic says that a clip of only 20 or 30 frames is enough information to give the system a good sense of how a person tends to move. Popovic imagines that the technology would be particularly useful for animators who make sports video games based on actual players. In fact, the technology is currently licensed to Redwood City, CA-based Electronic Arts, a maker of video games.
The worst technology of 2021
Face filters, billionaires in space, and home-buying algorithms that overpay all made our annual list of technology gone wrong.
A horrifying new AI app swaps women into porn videos with a click
Deepfake researchers have long feared the day this would arrive.
Meet Altos Labs, Silicon Valley’s latest wild bet on living forever
Funders of a deep-pocketed new "rejuvenation" startup are said to include Jeff Bezos and Yuri Milner.
A gene-edited pig’s heart has been transplanted into a human for the first time
The procedure is a one-off, and highly experimental, but the technique could help reduce transplant waiting lists in the future.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.