Abstract: Methods and systems are provided for training a model used for animating a facial expression of a game character. The method includes capturing mesh data of a first human actor using a three-dimensional (3D) camera to generate three-dimensional (3D) depth data of a face of the first human actor. In one embodiment, the 3D depth data is output as mesh files corresponding to a frame captured by the 3D camera. The method includes capturing two-dimensional (2D) point cloud data of the first human actor using a 2D camera. In one embodiment, the 2D point cloud data represents tracked dots present on the face of the first human actor. In another embodiment, the 2D point cloud data is processed to generate training label value files (tLVFs). The method includes processing the mesh data in time coordination with the tLVFs associated with the 2D point cloud data to train the model.

Abstract: Methods and systems are provided for training a model using a simulated character for animating a facial expression of a game character. The method includes generating facial expressions of the simulated character using input label value files (iLVFs). The method includes capturing mesh data of the simulated character using a virtual camera to generate three-dimensional (3D) depth data of a face of the simulated character. In one embodiment, the 3D depth data being output as mesh files corresponding to frames captured by the virtual camera. The method includes processing the iLVFs and the mesh data to train the model. In one embodiment, the model is configured to receive input mesh files from a human actor to generate output label value files (oLVFs) that are used for animating the facial expression of the game character. In this way, a real human actor is not required for training the model.

Abstract: A method for generating action sequence data for a character to be rendered in a video game is provided. The method includes, during recording of an actor in a performance space, providing a cue to the actor to perform an action that simulates interacting with a virtual object at a location in the performance space. The method also includes instructing a robot to move to the location in the performance space at which the actor is to simulate interaction with the virtual object, and instructing the robot to adjust a physical attribute of the robot when at the location. The physical attribute of the robot, when adjusted, is placed at a three-dimensional location in the performance space to simulate a scale of the virtual object with which the actor is to simulate interaction. The virtual object can be either an animated object or a non-animated object.

Abstract: Techniques are described for facilitating the coordination of audio video (AV) production using multiple actors in respective locations that are remote from each other, such that an integrated AV product can be generated by coordinating the activities of multiple remote actors in concert with one another. Motion capture (mocap) of multiple actors who are geographically distant from each other is facilitated.