Weta Digital Limited

An image generator generates images of a set of virtual fibers and effects thereon by processing representations of the set of fibers and computing representation of a virtual surface for a fiber clump in the set of virtual fibers from an artist parameter representing a desired artist effect, computing correlations of the vertices from a set of vertices based on associations of the vertices corresponding to the artist parameter, computing a set of relevant vertices using the correlations of the vertices, computing orthogonal gradients to produce a plurality of gradients using a selected vertex and the set of relevant vertices for the fiber clump, and computing the virtual surface of the fiber clump from the plurality of gradients.

Methods and systems for defocusing a rendered computer-generated image are presented. Pixel values for a pixel array are determined from a scene description. A blur amount for each pixel is determined based on a lens function representing a lens shape and/or effect. A blur amount and blur transparency value are determined for the pixel based on the lens function and pixel depth. A convolution range comprising pixels adjacent to the pixel is determined based on the blur amount. A blend color value is determined for the pixel based on the color value of the pixel, color values of pixels in the convolution range, and the blur transparency value. The blend color value is scaled based on the blend color value and a modified pixel color value is determined from scaled blend color values.

A programmatic arbitrary distribution of items in a modeling system may be provided. To perform the distribution, a surface may be received, and a point count of application points associated with locations on the surface may be determined. A density map may be applied over the surface to assign a density to portions of the surface for the point count. Application points are then assigned to locations on the surface according to the density map and a scattering function of the point count, where the scattering function is based on one or more repulsion forces between neighboring points. The one or more repulsion forces are treated as pushing each of the neighboring point apart. Thereafter, the surface may be provided having the application points scattered across the surface based on the one or more repulsion forces.

The present description relates relate to recalibration of a sensor device for performance capture, by detecting a miscalibration problem with sensor device and assessment of the problem. A recalibration system includes sensor devices initially calibrated at a recording site. A recording site change occurs and afterwards, a failure to match virtual rays projected from one sensor device with virtual rays projected from the active marker is detected. In response to determining the failure, the active marker is signaled to emit a unique display of light. The failure of the rays to match is assessed based on whether sensor devices capture the unique display of light. Three-dimensional (3-D) coordinates of an active marker is reconstructed from marker data of the calibrated sensor devices. A problematic sensor device is recalibrated based on the assessment, using the 3-D coordinates of the active marker from marker data of the remaining calibrated sensor devices, without stopping the recording.

An aspect provides a computer-implemented method for constructing evaluation logic associated with an animation software package. The method comprises receiving at least one software module, the at least one software module including at least one evaluator; writing the at least one software module to at least one executable code object; and maintaining data for the at least one software module in a contiguous block of memory for use by the software module.

In an image processing system, an image insertion is to be included onto, or relative to, a first and second frame, each depicting images of a set of objects of a geometric model. A point association is determined for a depicted object that is depicted in both the first frame and the second frame, representing reference coordinates in a virtual scene space of a first location on the depicted object independent of at least one position change and a mapping of a first image location in the first image to where the first location appears in the first image. A corresponding location in the second image is determined based on where the first location on the depicted object appears according to the reference coordinate in the virtual scene space and a second image location on the second image where the first location appears in the second image.

In an image processing system, artist user interface provides for user input of specifications for an inserted object, specified in frame space. The inserted objects can be specified in frame space but can be aligned with object points in a virtual scene space. For other frames, where the object points move in the frame space, the object movements are applied to the inserted object in the frame space. The alignment can be manual by the user or programmatically determined.

A character rig may be representable as a data structure specifying a plurality of articulated character parts, an element tree specifying relations between character parts, and a set of constraints on the character parts. After receiving rotoscoping movement input data corresponding to attempted alignments of movements of at least some of the character parts with elements moving in a captured live action scene, a rotoscoping constraints may be received. The rotoscoping constraint may include at least a first constraint on the character rig other than a second constraint specified by the data structure of the character rig, Thereafter, rig movement inputs for a second set of character parts distinct from the first set of character parts may be accepted and the character rig may be moved according to the rig movement inputs while constrained by the rotoscoping constraints.

A representation of a surface of one or more objects is positioned in a virtual space is obtained in a computer animation system. Thereafter, a guide curve specification of a guide curve in the virtual space relative to the surface is received. Thereafter, the computer animation system computes a first set of tangent vector values for differentiable locations along the guide curve and computes a second set of tangent vector values for nondifferentiable locations along the guide curve. Using the first set and second set, the computer animation system computes a third set of tangent vector values for locations on the surface other than locations along the guide curve and computes a tangent vector field over the surface from at least the first set of tangent vector values, the second set of tangent vector values, and the third set of tangent vector values.

In an image processing system, a scan of an actor is converted to a high-resolution two-dimensional map, which is converted to low-resolution map and to a facial rig model. Manipulations of the facial rig create a modified facial rig. A new low-resolution two-dimensional map can be obtained of the modified facial rig and a neural network can be used to generate a new high-resolution two-dimensional map that can be used to generate a mesh that is a mesh of the scan, modified by the manipulations of the facial rig.