Auto Animator
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.
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.
The problem with plug-in hybrids? Their drivers.
Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.
Google DeepMind’s new generative model makes Super Mario–like games from scratch
Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.
How scientists traced a mysterious covid case back to six toilets
When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.