Abstract: The present invention relates to computer capture of object motion. More specifically, embodiments of the present invention relate to capturing of facial movement or performance of an actor. Embodiments of the present invention provide a head-mounted camera system that allows the movements of an actor's face to be captured separately from, but simultaneously with, the movements of the actor's body. In many embodiments, multiple cameras are provided mounted on a bracket for placement on the head of an actor. In some embodiments, the cameras record grayscale images of an actor's face, which has been marked with dots of makeup. In many embodiments, the cameras record images of an actor's face from at least two angles.

Abstract: The present invention relates to computer capture of object motion. More specifically, embodiments of the present invention relate to capturing of facial movement or performance of an actor. Embodiments of the present invention provide a head-mounted camera system that allows the movements of an actor's face to be captured separately from, but simultaneously with, the movements of the actor's body. In many embodiments, multiple cameras are provided mounted on a bracket for placement on the head of an actor. In some embodiments, the cameras record grayscale images of an actor's face, which has been marked with dots of makeup. In many embodiments, the cameras record images of an actor's face from at least two angles.

Abstract: The present invention relates to computer capture of object motion. More specifically, embodiments of the present invention relate to capturing of facial movement or performance of an actor. Embodiments of the present invention provide a head-mounted camera system that allows the movements of an actor's face to be captured separately from, but simultaneously with, the movements of the actor's body. In some embodiments of the present invention, a method of motion capture of an actor's performance is provided. A self-contained system is provided for recording the data, which is free of tethers or other hard-wiring, is remotely operated by a motion-capture team, without any intervention by the actor wearing the device. Embodiments of the present invention also provide a method of validating that usable data is being acquired and recorded by the remote system.

Abstract: A method for efficiently manipulating 3D scenes recorded by a virtual camera using a computer system comprised of projectors, graphics accelerators, one or more CPUs, instances of 3D rendering software, and a MIDI interface, includes receiving from the MIDI controller camera parameters, defining left camera and right camera parameters based on the camera parameters, determining left and right images based upon left and right camera parameters, projecting left and right images, viewing left and right images, integrating left and right images to represent a 3D scene, manipulating the 3D scene until the user is satisfied, and storing the left and right camera parameters, and storing the left and right images.

Abstract: The present invention relates to computer capture of object motion. More specifically, embodiments of the present invention relate to capturing of facial movement or performance of an actor. Embodiments of the present invention provide a head-mounted camera system that allows the movements of an actor's face to be captured separately from, but simultaneously with, the movements of the actor's body. In many embodiments, multiple cameras are provided mounted on a bracket for placement on the head of an actor. In some embodiments, the cameras record grayscale images of an actor's face, which has been marked with dots of makeup. In many embodiments, the cameras record images of an actor's face from at least two angles.

Abstract: A method for a computer system includes displaying a first plurality of images to a user on a display at a uniform rate wherein the images of the first plurality of images are determined in response to a first plurality of marks associated with a virtual camera location curve within a three-dimensional scene, receiving a plurality of user inputs from a user input device, while the user views the first plurality of images at the uniform rate, determining a second plurality of marks in response to the first plurality of marks associated with the curve and the plurality of user inputs, determining a second plurality of images in response to the second plurality of marks associated with the curve, storing the second plurality of marks associated with the curve in a memory, and displaying the second plurality of images to the user on the display at the uniform rate.

Abstract: A method for a computer system includes receiving a surface deformation for an object from a computer system user, wherein an object model comprises animation variables used to determine the surface of the object model, determining at least one pre-defined object pose from pre-defined object poses in response to the surface deformation, wherein the predefined object poses includes a first predefined object pose and comprises animation variable values, wherein the animation variable values are determined from physical motion capture data of surface positions of a physical representation of the object posed in a first pose, posing the object model in a pose in response to at least the animation variable values, and displaying the object model in the pose on a display to the computer system user.

Abstract: A method for a computer system comprising receiving a displacement for a first object model surface from a user determined in response to a first physical motion captured pose, determining a weighted combination of a first displacement group and a second displacement group from the displacement, wherein the first displacement group is determined from displacements between the first object model surface and a second object model surface, wherein the second object model surface is determined from displacements between a second physical motion captured pose, wherein the second displacement group is determined from displacements between the first object model surface and a third object model surface, wherein the third object model surface is determined from a third physical motion captured pose, determining a fourth object model surface from the first object model surface and the weighted combination, and displaying the fourth object model surface to the user on a display.

Abstract: The present invention relates to computer capture of object motion. More specifically, embodiments of the present invention relate to capturing of facial movement or performance of an actor. Embodiments of the present invention provide a mounting bracket for a head-mounted motion capture camera system. In many embodiments, the mounting bracket includes a helmet that is positioned on the actor's head and mounting rods on either side of the helmet that project toward the front of the actor that may be flexibly repositioned. Cameras positioned on the mounting rods capture images of the actor's face.

Abstract: A method for a computer system includes receiving global positional data associated with a set of markers from a plurality of markers associated with a surface of an object at one or more time instances, wherein global positional data associated with a first marker from the plurality of markers is absent from a first time instance, using local statistical methods to determine global positional data associated with the first marker at the first time instance in response to the global positional data associated with the set of markers at the one or more time instances, and determining a model of the object in response to the global positional data associated with the set of markers and the global positional data associated with the first marker.

Abstract: A method for a computer system includes receiving a first camera image of a 3D object having sensor markers, captured from a first location, at a first instance, receiving a second camera image of the 3D object from a second location, at a different instance, determining points from the first camera image representing sensor markers of the 3D object, determining points from the second camera image representing sensor markers of the 3D object, determining approximate correspondence between points from the first camera image and points from the second camera image, determining approximate 3D locations some sensor markers of the 3D object, and rendering an image including the 3D object in response to the approximate 3D locations.