Real-time automatic concatenation of 3D animation sequences

摘要

Systems and methods for generating and concatenating 3D character animations are described including systems in which recommendations are made by the animation system concerning motions that smoothly transition when concatenated. One embodiment includes a server system connected to a communication network and configured to communicate with a user device that is also connected to the communication network. In addition, the server system is configured to generate a user interface that is accessible via the communication network, the server system is configured to receive high level descriptions of desired sequences of motion via the user interface, the server system is configured to generate synthetic motion data based on the high level descriptions and to concatenate the synthetic motion data, the server system is configured to stream the concatenated synthetic motion data to a rendering engine on the user device, and the user device is configured to render a 3D character animated using the streamed synthetic motion data.

主权项

1. A method for providing synthetic motion data from a server system to user device for use in animating a Three-Dimensional (3D) character comprising:
obtaining motion data from a storage device using the server system, wherein the motion data includes labels the describe high level characteristics of a motion and describes changes of 3D animation variables of a character over time; training a motion model using the server system wherein the motion model is based on the obtained motion data using supervised learning wherein the motion model forms association between the high level characteristics and the motion stored in the storage device; receiving a high level description of a sequence of desired motions wherein the high level description includes high level characteristics of a plurality of sequential motions in the sequence from a user device in the server system via a user interface generated by a server system; generating synthetic motion data for each of the plurality of sequential motions using the server system based upon the high level characteristics of each of the plurality of sequential motions and the motion model; generating synthetic data for transitions between each pair of sequential motions in the sequence using the server system; concatenating the synthetic motion data for the plurality of sequential motions and the transitions using the server system; streaming the concatenated motion data from the server system to the user device; and rendering an animation of a 3D character based upon the streamed synthetic motion data using the user device.