Abstract: A deep neural network can be trained to output motion or deformation information for a character that is representative of the character uttering speech contained in audio input, which is accurate for an emotional state of the character. The character can have different facial components or regions (e.g., head, skin, eyes, tongue) modeled separately, such that the network can output motion or deformation information for each of these different facial components. During training, the network can be provided with emotion and/or style vectors that indicate information to be used in generating realistic animation for input speech, as may relate to one or more emotions to be exhibited by the character, a relative weighting of those emotions, and any style or adjustments to be made to how the character expresses that emotional state. The network output can be provided to a renderer to generate audio-driven facial animation that is emotion-accurate.

Abstract: A three-dimensional (3D) model of an object is recovered from two-dimensional (2D) images of the object. Each image in the set of 2D images includes the object captured from a different camera position and deformations of a base mesh that defines the 3D model may be computed corresponding to each image. The 3D model may also include a texture map that represents the lighting and material properties of the 3D model. Recovery of the 3D model relies on analytic antialiasing to provide a link between pixel colors in the 2D images and geometry of the 3D model. A modular differentiable renderer design yields high performance by leveraging existing, highly optimized hardware graphics pipelines to reconstruct the 3D model. The differential renderer renders images of the 3D model and differences between the rendered images and reference images are propagated backwards through the rendering pipeline to iteratively adjust the 3D model.

Abstract: Apparatuses, systems, and techniques are presented to generate media content.

Abstract: A three-dimensional (3D) model of an object is recovered from two-dimensional (2D) images of the object. Each image in the set of 2D images includes the object captured from a different camera position and deformations of a base mesh that defines the 3D model may be computed corresponding to each image. The 3D model may also include a texture map that represents the lighting and material properties of the 3D model. Recovery of the 3D model relies on analytic antialiasing to provide a link between pixel colors in the 2D images and geometry of the 3D model. A modular differentiable renderer design yields high performance by leveraging existing, highly optimized hardware graphics pipelines to reconstruct the 3D model. The differential renderer renders images of the 3D model and differences between the rendered images and reference images are propagated backwards through the rendering pipeline to iteratively adjust the 3D model.

Abstract: The present disclosure relates to a motion edit method for editing the motion of an articulated object using a computing device with a touch screen, including a) when any one of a joint path and a body line of an articulated object is selected by a user, setting a position constraint of higher level joint according to the user's sketching input and joint hierarchy, and b) generating motion of the articulated object for which the constraint is set.

Abstract: The present disclosure relates to a motion edit method for editing the motion of an articulated object using a computing device with a touch screen, including a) when any one of a joint path and a body line of an articulated object is selected by a user, setting a position constraint of higher level joint according to the user's sketching input and joint hierarchy, and b) generating motion of the articulated object for which the constraint is set.

Abstract: Provided are a method, an apparatus and a system for dense graph simplification, and a recording medium for the same. The method includes receiving an original graph and extracting a plurality of salient points, which minimize a cost representing a greatest vertical distance between the original graph and each of a plurality of lines connecting two data points in a designated region on the original graph; and outputting a simplified graph in which the extracted salient points are connected. Thus, optimal results are ensured in dense graph simplification, and interactive control is allowed for a user.

Abstract: Provided are a method, an apparatus and a system for dense graph simplification, and a recording medium for the same. The method includes receiving an original graph and extracting a plurality of salient points, which minimize a cost representing a greatest vertical distance between the original graph and each of a plurality of lines connecting two data points in a designated region on the original graph; and outputting a simplified graph in which the extracted salient points are connected. Thus, optimal results are ensured in dense graph simplification, and interactive control is allowed for a user.