Facebook Technologies, LLC

Meta Platforms Technologies, LLC

Melinda Ozel

William Arthur Hugh Steptoe

Michael Andrew Howard

Timothy Naylor

Giovanni F Nakpil

Elif Albuz

Tong Xiao

Sidi Fu

The disclosed computer-implemented method may include identifying a set of action units (AUs) associated with a face of a user. Each AU may be associated with a muscle group engaged by the user to produce a viseme associated with a sound produced by the user. The method may also include, for each AU in the set of AUs, determining a set of AU parameters associated with the AU and the viseme. The set of AU parameters may include (1) an onset curve, and (2) a falloff curve. The method may also include (1) detecting that the user has produced the sound, and (2) directing a computer-generated avatar to produce the viseme in accordance with the set of AU parameters in response to detecting that the user is producing the sound. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods for improving animation of computer-generated avatars

The disclosed computer-implemented method may include identifying a muscle group engaged by a user to execute a predefined body action by (1) capturing a set of images of the user while the user executes the predefined body action, and (2) associating a feature of a body of the user with the muscle group based on the predefined body action and the set of images. The method may also include determining, based on the set of images, a set of parameters associated with the user, the muscle group, and the predefined body action. The method may also include directing a computer-generated avatar that represents the body of the user to produce the predefined body action in accordance with the set of parameters. Various other methods, systems, and computer-readable media are also disclosed.

Disclosed herein includes a system, a method, and a non-transitory computer readable medium for applying an expression to an avatar. In one aspect, a class of an expression of a face can be determined according to a set of attributes indicating states of portions of the face. In one aspect, a set of blendshapes with respective weights corresponding to the expression of the face can be determined according to the class of the expression of the face. In one aspect, the set of blendshapes with respective weights can be provided as an input to train a machine learning model. In one aspect, the machine learning model can be configured, via training, to generate an output set of blendshapes with respective weights, according to an input image. An image of an avatar may be rendered according to the output set of blendshapes with respective weights.

System and method for applying an expression to an avatar

Growing community of inventors

San Francisco, CA, United States of America

Melinda Ozel