We are excited to announce DeepMoji: DeepMotion’s Digital Avatar Solution for user tracking from 2D video. The technology, as shown running in real-time in the video above, allows for the instantaneous character animation of 3D avatars from home devices. Businesses can use DeepMotion’s Avatar Solutions for a range of applications, such as full body avatars in Virtual Reality or Augmented Reality, as well as cloud-based animation creation.
Leveraging research breakthroughs from the Computer Vision field known as “3D pose estimation”, DeepMotion can now transfer the motions of people onto digital characters in real time. The DeepMotion solution derives additional accuracy from the physics-based character model used to simulate the avatars—adding necessary body constraints that help translate quick or complicated motions from 2D to 3D. This technology opens the doors to new forms of expression and connection, in addition to low-cost motion capture for animation.
DeepMotion’s Digital Avatar solution is one facet of DeepMotion Neuron, our product for interactive character solutions. DeepMotion products bridge physical and digital motion for virtual characters and machines. Using physics simulation, computer vision, and machine learning, DeepMotion reconstructs realistic motion from real-world examples.
DeepMotion is a pioneer in the emerging field of Motion Intelligence. The company is building a platform powered by advanced physics simulation, computer vision, and machine learning. Led by members from Blizzard, Pixar, Disney, ROBLOX, Microsoft, Ubisoft, Stanford, CMU and Tsinghua, DeepMotion is leveraging decades of experience in the field to help individuals and teams bridge digital and physical motion. The company was founded in 2014, and is headquartered in Redwood City, CA.