The most popular and comprehensive Open Source ECM platform
Meta/Facebook and other companies are betting big that the future of on-line social interactions will be a network of virtual worlds that is being called the metaverse. Participants in virtual reality of the metaverse will be able to interact with others through dynamic virtual representations of themselves called avatars which they will be able to control.
Meta poured $10 billion in 2021 into research for developing the technologies to enable a compelling metaverse experience. An important capability will be the handling of 3D avatar animation. Because realistic 3D avatar rendering has been hard to do, researchers are increasingly turning to artificial intelligence to help achieve better animation of 3D human-like avatars.
Jessica Hodgins, professor of computer science and robotics at Carnegie Mellon University, described the tediousness often required with traditional computer animation to Engadget, saying that “with motion capture, the data that we have is all that we have, in the sense that if we capture somebody dribbling a ball across the room at a particular speed, then we have it at that speed. We don’t have the ability to easily adapt it to turning, or running at a different speed, or dribbling with a different pattern.”
But, now computer animation algorithms are adopting AI techniques. The 3D animation work by Hodgins at Carnegie Mellon uses a techniques called “deep reinforcement learning“.
Hodgins said that “if you want the character to do something slightly different, turn a little bit more sharply or something like that, that’s all within the space of what the algorithm can do. Whereas with motion capture, you just have exactly the sequence you captured.”
The impressive realistic animation shown above is the work of another research group in Switzerland. The ability to create realistic 3D animations with relatively low computing power will be a major enabler in making a more compelling virtual metaverse.