Abstract: A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor configured to execute the instructions to perform a method that includes receiving multiple representations of one or more expressions of an object. Each of the representations includes position information attained from one or more images of the object. The method also includes producing an animation model from one or more groups of controls that respectively define each of the one or more expressions of the object as provided by the multiple representations. Each control of each group of controls has an adjustable value that defines the geometry of at least one shape of a portion of the respective expression of the object. Producing the animation model includes producing one or more corrective shapes if the animation model is incapable of accurately presenting the one or more expressions of the object as provided by the multiple representations.

Abstract: A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor configured to execute the instructions to perform a method that includes receiving multiple representations of an object. Each of the representations includes position information of the object and corresponds to an instance in time. For at least one of the representations, the method includes defining a contour that represents a movable silhouette of a surface feature of the object. The method also includes producing a deformable model of the surface of the object from the defined contour and from the at least one representation of the object.

Abstract: A system includes a computing device that includes a memory and a processor configured to execute instructions to perform a method that includes receiving multiple representations of one or more expressions of an object. Each representation includes position information attained from one or more images of the object. The method also includes producing an animation model from one or more groups of controls that respectively define each of the one or more expressions of the object as provided by the multiple representations. Each control of each group of controls has an adjustable value that defines the geometry of at least one shape of a portion of the respective expression of the object. Producing the animation model includes producing one or more corrective shapes if the animation model is incapable of accurately presenting the one or more expressions of the object as provided by the multiple representations.

Abstract: In some embodiments a method of transferring facial expressions from a subject to a computer-generated character is provided where the method includes receiving positional information from a motion capture session of the subject representing a performance having facial expressions to be transferred to the computer-generated character, receiving a first animation model that represents the subject, and receiving a second animation model that represents the computer-generated character. Each of the first and second animation models can include a plurality of adjustable controls that define geometries of the model and that can be adjusted to present different facial expressions on the model, and where the first and second animation models are designed so that setting the same values for the same set of adjustable controls in each model generates a similar facial poses on the models.

Abstract: A method of motion capture may include accessing a 3D model of a subject, and associating the 3D model of the subject with a 2D representation of the subject in a plurality of frames. The method may also include identifying a change to the 2D representation of the subject between two or more of the plurality of frames, and deforming the 3D model in a virtual 3D space. In some embodiments, the deforming may be based on the identified change to the 2D representation and at least one constraint restricting how the 3D model can be deformed.

Abstract: A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor configured to execute the instructions to perform a method that includes receiving multiple representations of an object. Each of the representations includes position information of the object and corresponds to an instance in time. For at least one of the representations, the method includes defining a contour that represents a movable silhouette of a surface feature of the object. The method also includes producing a deformable model of the surface of the object from the defined contour and from the at least one representation of the object.

Abstract: In some embodiments a method of transferring facial expressions from a subject to a computer-generated character is provided where the method includes receiving positional information from a motion capture session of the subject representing a performance having facial expressions to be transferred to the computer-generated character, receiving a first animation model that represents the subject, and receiving a second animation model that represents the computer-generated character. Each of the first and second animation models can include a plurality of adjustable controls that define geometries of the model and that can be adjusted to present different facial expressions on the model, and where the first and second animation models are designed so that setting the same values for the same set of adjustable controls in each model generates a similar facial poses on the models.

Abstract: A system includes a computing device that includes a memory configured to store instructions. The computing device also includes a processor configured to execute the instructions to perform a method that includes producing an animation model from one or more representations of an object provided from a deformable likeness of the object. The one or more representations are based upon position information from a collection of images of the object captured by at least one camera. The method also includes refining the animation model to produce representations that substantially match the one or more representations provided by the deformable likeness of the object. Refining the animation model is based upon the position information from the collection of images of the object and one or more constraints.

Abstract: This disclosure describes technology, which can be implemented as a method, apparatus, and/or computer software embodied in a computer-readable medium, capable of deforming internal geometry within an outer geometry to account for light bending due to refraction, for example, for real-time modeling of a gaze direction of a 3D computer generated character's eyes. In some implementations, internal eye geometry can be deformed to capture the effect of refraction in real-time such that the gaze direction of a 3D character's eyes can be modeled during an animation phase prior to a rendering phase in the production of a computer generated motion picture.

Abstract: A computer program product tangibly embodied in a computer-readable storage medium includes instructions that when executed by a processor perform a method. The method includes identifying a frame of a video sequence, transforming a model into an initial guess for how the region appears in the frame, performing an exhaustive search of the frame, performing a plurality of optimization procedures, wherein at least one additional model parameter is taken into account as each subsequent optimization procedure is initiated. A system includes a computer readable storage medium, a graphical user interface, an input device, a model for texture and shape of the region, the model generated using the video sequence and stored in the computer readable storage medium, and a solver component.

Abstract: A computer-implemented method for providing retargeting of actor motion includes: receiving, in a computer system, an input generated by user selection of at least one of multiple real-time constraint scenarios, each real-time constraint scenario corresponding to a relationship between motion capture information from an actor and a position or movement of a character driven by the motion capture information; activating, based on the selected real-time constraint scenario, one or more of multiple limb solvers for the character which determines at least a first joint angle for a corresponding character limb; registering, for at least one character limb where the corresponding limb solver is not activated, a corresponding joint angle from the motion capture information as a second joint angle; and determining a root location for the character based on at least the first and second joint angles.

Abstract: A motion library can be created by generating motion feature vectors for at least some of multiple frames of a video sequence using a 3D mesh, each motion feature vector corresponding to characteristics of the body deformation in one of the frames. The A user can select a subset of the frames. For each frame in the subset, the user can define settings for controls of an animation character, the settings selected by the user to correspond to the body deformation in the respective frame. Mappings are generated using the settings and the motion feature vectors, the mappings regulating the controls based on multiple motion feature vectors. The motion library can be used to generate an animation from an actor performance.

Abstract: A computer program product tangibly embodied in a computer-readable storage medium includes instructions that when executed by a processor perform a method. The method includes identifying a frame of a video sequence, transforming a model into an initial guess for how the region appears in the frame, performing an exhaustive search of the frame, performing a plurality of optimization procedures, wherein at least one additional model parameter is taken into account as each subsequent optimization procedure is initiated. A system includes a computer readable storage medium, a graphical user interface, an input device, a model for texture and shape of the region, the model generated using the video sequence and stored in the computer readable storage medium, and a solver component.

Abstract: A method of motion capture may include accessing a 3D model of a subject, and associating the 3D model of the subject with a 2D representation of the subject in a plurality of frames. The method may also include identifying a change to the 2D representation of the subject between two or more of the plurality of frames, and deforming the 3D model in a virtual 3D space. In some embodiments, the deforming may be based on the identified change to the 2D representation and at least one constraint restricting how the 3D model can be deformed.

Abstract: A first frame includes a first 2D image of a motion capture subject in the real 3D space. A 3D model is deformed into a first deformation and placing the deformed 3D model in a virtual 3D space in a first location so that the deformed 3D model corresponds to the first 2D image. A second frame includes a second 2D image of the motion capture subject in the real 3D space. 2D changes in the second 2D image relative to the first 2D image are tracked. The 2D changes are projected on the virtual 3D space as 3D constraints. Based on the second 2D image, the 3D model is again deformed into a second deformation and placing the 3D model in the virtual 3D space in a second location in conformance with the 3D constraints.

Abstract: A computer program product tangibly embodied in a computer-readable storage medium includes instructions that when executed by a processor perform a method. The method includes identifying a frame of a video sequence, transforming a model into an initial guess for how the region appears in the frame, performing an exhaustive search of the frame, performing a plurality of optimization procedures, wherein at least one additional model parameter is taken into account as each subsequent optimization procedure is initiated. A system includes a computer readable storage medium, a graphical user interface, an input device, a model for texture and shape of the region, the model generated using the video sequence and stored in the computer readable storage medium, and a solver component.

Abstract: The subject matter of this specification can be embodied in, among other things, a system that includes a correspondence generator that determines a distance-based mapping between a set of points in a source object and a point in a target object and stores the distance-based mapping in a surface map. The system also includes an attribute transfer module that transfers surface attributes that determine an appearance or deformation of the set of points in the source object to the point in the target object using the surface map. The system also includes an attribute editor that receives a selection of a region of the target object and applies an interpolation algorithm that determines new values for surface attributes in the selected region from neighboring points in the target object.