Facebook Technologies, LLC

Meta Platforms Technologies, LLC

Oracle International Corporation

Oracle America, Inc.

Tong Xiao

Elif Albuz

Peihong Guo

James Allan Booth

Sidi Fu

Rajendran Panda

Evgeny Zatepyakin

Melinda Ozel

Shu Liang

Ruiming Li

Ted Hong

Mengqian Liu

Xiaomi Mao

In one embodiment, one or more computing systems may access a plurality of images corresponding to a portion of a face of a user. The plurality of images is captured from different viewpoints by a plurality of cameras coupled to an artificial-reality system worn by the user. The one or more computing systems may synthesize, using a machine-learning model, to generate a synthesized image corresponding to the portion of the face of the user. The one or more computing systems may access a three-dimensional (3D) facial model representative of the face of the user and generate a texture image by projecting the synthesized image onto the 3D facial model from a specific camera pose. The one or more computing systems may cause an output image of a facial representation of the user to be rendered using at least the 3D facial model and the texture image.

Camera reprojection for faces

In one embodiment, one or more computing systems may receive an image of a portion of a face of a first user. The one or more computing systems may access a three-dimensional (3D) facial model representative of the face of the first user. The one or more computing systems may identify one or more facial features captured in the image and determine a camera pose relative to the 3D facial model based on the identified one or more facial features in the image and predetermined feature locations on the 3D facial model. The one or more computing systems may determine a mapping relationship between the image and the 3D facial model by projecting the image of the portion of the face of the first user onto the 3D facial model from the camera pose and cause an output image of a facial representation of the first user to be rendered.

Disclosed herein includes a system, a method, and a non-transitory computer readable medium for rendering a three-dimensional (3D) model of an avatar according to an audio stream including a vocal output of a person and image data capturing a face of the person. In one aspect, phonemes of the vocal output are predicted according to the audio stream, and the predicted phonemes of the vocal output are translated into visemes. In one aspect, a plurality of blendshapes and corresponding weights are determined, according to the corresponding image data of the face, to form the 3D model of the avatar of the person. The visemes may be combined with the 3D model of the avatar to form a 3D representation of the avatar, by synchronizing the visemes with the 3D model of the avatar in time.

System and method for rendering three dimensional face model based on audio stream and image data

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

A method for the simulation of a circuit is disclosed. The method may include the determination of parasitic circuit elements, and the determination of one or more operational parameters dependent upon at least the parasitic circuit elements. A model of the parasitic circuit elements may then be generated based upon the one or more operational parameters. The circuit may then be simulated using the model of the parasitic circuit elements to determine a performance level of the circuit. At least one active circuit element may be modified in response to determining that the performance level does not meet a goal.

Method for estimation of delays and slews during circuit optimization

Implementations of the present disclosure involve an apparatus and/or method for identifying and classify nodes of an electrical circuit design to account for hold time violations occurring within the circuit. The nodes may be ordered based on a criticality of the nodes that may aid in identifying those nodes of the circuit where hold time violations may be corrected. In one embodiment, the criticality may relate to the number of potentially violating paths that utilize the identified nodes such that corrective measures applied at those nodes may correct several hold time violating paths. In addition, criticality may be scaled utilizing an available buffer library and other timing information. Thus, by utilizing the methods and/or apparatuses of the present disclosure, the locations where timing violation corrective measures may be applied that improve or correct several violating data paths at once may be identified in such a manner so as to reduce the number of overall corrections made to the circuit design, reducing the cost and necessary time associated with the corrections.

Growing community of inventors

San Jose, CA, United States of America

Tong Xiao