Animated characters can learn from online tutorials, too.<\/p>\n
A new computer program teaches virtual avatars new skills, such as dances, acrobatic stunts and martial art moves, from YouTube videos. This kind of system, described in the November ACM Transactions on Graphics<\/em>, could render more physically coordinated characters for movies and video games, or serve as a virtual training ground for robots.<\/p>\n \u201cI was really impressed\u201d by the program, says Daniel Holden, a machine-learning researcher at Ubisoft La Forge in Montreal not involved in the work. Rendering accurate, natural-looking movements based on everyday video clips \u201chas always been a goal for researchers in this field.\u201d<\/p>\n Animated characters typically have learned full-body motions by studying motion capture data, collected by a camera that tracks special markers attached to actors bodies. But this technique requires special equipment and often works only indoors.<\/p>\n The new program leverages a type of computer code known as an artificial neural network, which roughly mimics how the human brain processes information. Trained on about 100,000 images of people in various poses, the program first estimates an actors pose in each frame of a video clip. Then, it teaches a virtual avatar to re-create the actors motion using reinforcement learning, giving the character a virtual \u201creward\u201d when it matches the video actors pose in a frame.<\/p>\n Computer scientist Jason Peng and colleagues at the University of California, Berkeley, fed YouTube videos into the system to teach characters to do somersaults, backflips, vaulting and other stunts<\/a>.<\/p>\n\n\n
\n