DeepMotion has launched DeepMotion Neuron, the first tool for completely procedural, physical character animation, for presale. The cloud application trains digital characters to develop physical intelligence using advanced artificial intelligence (AI), physics and deep learning. With guidance and practice, digital characters can now achieve adaptive motor control just as humans do, in turn allowing animators and developers to create more lifelike and responsive animations than those possible using traditional methods.
DeepMotion Neuron is a behavior-as-a-service platform that developers can use to upload and train their own 3D characters, choosing from hundreds of interactive motions available via an online library. Neuron will enable content creators to tell more immersive stories by adding responsive actors to games and experiences. By handling large portions of technical animation automatically, the service also will free up time for artists to focus on expressive details.
DeepMotion Neuron is built on techniques identified by researchers from DeepMotion and Carnegie Mellon University who studied the application of reinforcement learning to the growing domain of sports simulation, specifically basketball, where real-world human motor intelligence is at its peak. After training and optimization, the researchers’ characters were able to perform interactive ball-handling skills in real-time simulation. The same technology used to teach digital actors how to dribble can be applied to any physical movement using Neuron.
DeepMotion Neuron’s cloud platform is slated for release in Q4 of 2018. During the DeepMotion Neuron prelaunch, developers and animators can register on the DeepMotion website for early access and discounts.