Abstract: Methods, systems, and articles of manufacture are disclosed for creating posed models. In various embodiments, deformations resulting from posing a model can be represented in a set of training poses. The sets of training poses for the model and a desired target pose (e.g., a simulated or sculpted pose) can be used to create a final pose for the model. Arbitrary deformer activation weights can be determined by projecting a target pose onto the set of training poses. The deformer activation weights can be applied to one or more deformers to approximate the desired pose.

Abstract: Light field imaging systems, and in particular light field lenses that can be mated with a variety of conventional cameras (e.g., digital or photographic/film, image and video/movie cameras) to create light field imaging systems. Light field data collected by these light field imaging systems can then be used to produce 2D images, right eye/left eye 3D images, to refocus foreground images and/or background images together or separately (depth of field adjustments), and to move the camera angle, as well as to render and manipulate images using a computer graphics rendering engine and compositing tools. A doublet lenslet array element for use in light field imaging systems includes a first lenslet array element having a first plurality of lenslet array elements, and a second lenslet array element having a first plurality of lenslet array elements, wherein the first lenslet array element is coupled in close proximity to the second lenslet array element.

Abstract: A method for color grading within a component color space associated with a display includes receiving a source image comprising a plurality of pixels, wherein each pixel is associated with a color comprising a plurality of color component values in the component color space, wherein the component color space comprises RGB, and wherein a pixel is associated with a color inside a gamut of the display but outside a gamut of a target media, receiving a color grading signal from a user, modifying the color associated with the pixel from the plurality of pixels in response to the color grading signal, to form a graded image comprising the pixel, wherein the pixel is associated with a graded color comprising a plurality of color component values, displaying the graded image on the display to the user, automatically performing a gamut remapping of the graded color associated with the pixel, to form a gamut remapped image comprising the pixel, wherein the pixel is associated with a gamut remapped color comprising a p

Abstract: Programmable or user-defined visibility functions can be defined to achieve rendering effects and eliminate rendering errors. A renderer traverses the set of geometry samples potentially visible to an image sample. Rather than accumulate opacity and color in strict depth order, the renderer can invoke visibility functions associated with some or all of the geometry samples. Each geometry sample's visibility function can access attributes of any other geometry sample associated with the image sample. Furthermore, each geometry sample's visibility function can identify the position of its associated geometry sample and any other geometry samples in the depth sequence of geometry samples associated with an image sample. A visibility function can return any arbitrary value based on attributes of its associated geometry sample, attributes of other geometry samples associated with the image sample, and/or the position of geometry samples in the depth sequence associated with the image sample.

Abstract: An edge-preserving diffusion filter maintains the sharp edges in images while smoothing out image noise. An edge-preserving diffusion filter applies an edge-preserving smoothing filter to an image to form a filtered image. The modified image is then blurred by a blurring filter to form a blurred image. The modified image and the blurred image are blended together to form an output image based on an error metric associated with each pixel. The edge-preserving diffusion filter may be utilized to perform a multilevel decomposition of the image. The edge-preserving diffusion filter may be applied to an unfiltered image to produce a base image. The difference between the unfiltered image and the base image defines a detail image. The detail image may be used as the input for recursively generating additional levels of detail. The multilevel decomposition may utilize filter kernels associated with different contrast levels for each iteration.

Abstract: Techniques are disclosed for orienting (or reorienting) properties of computer-generated models, such as those associated with dynamic models or simulation models. Properties (e.g., material or physical properties) that influence the behavior of a dynamic or simulation model (e.g., a complex curve model representing a curly hair) may be oriented or re-oriented as desired using readily available reference frames. These references frame may be obtained using a proxy model that corresponds to the dynamic or simulation model in a less computationally expensive manner in some embodiments than some techniques for determining reference frames directly using the dynamic or simulation model. In some embodiments, the proxy model may include a smoothed version of the dynamic or simulation model. In other embodiments, the proxy model may include a filtered or simplified version of the dynamic or simulation model.

Abstract: Techniques are disclosed for accounting for features of computer-generated dynamic or simulation models being at different scales. Some examples of dynamic or simulation models may include models representing hair, fur, strings, vines, tails, or the like. In various embodiments, features at different scales in a complex dynamic or simulation model can be treated differently when rendered and/or simulated.

Abstract: The space including a particle system is discretized into volume elements. Signed distance values at each time and velocity values at a time are assigned to volume elements based on the particle system. The each volume element's position at the current time is extrapolated to an additional position at each additional time based on its respective velocity value. A temporally coherent signed distance value for each volume element is determined from its signed distance value and the signed distance values at the associated additional position at each additional time. A surface extracted from the temporally coherent signed distance values will be temporally coherent over the interval including the current time and the one or more additional times. Arbitrary surface properties may also be associated with volume elements and temporally coherent surface property values may be determined for each volume element using its respective velocity value in a similar manner.

Abstract: A method for a computer system includes retrieving from a computer readable medium a first irradiance approximation for a plurality of light sources for a first distance in the midfield from the light sources; retrieving from the computer readable medium a second irradiance approximation for the plurality of light sources for a second distance in the farfield, where the second distance is greater than the first distance; and interpolating the first irradiance approximation and the second irradiance approximation to generate a third irradiance approximation for a point having a third distance from the light sources.

Abstract: Realistic sprays for simulated fluids are created by adding a set of spray particles to a boundary region just below the fluid surface. The fluid surface is determined by solving a level set equation for a zero level corresponding to the fluid surface. Additionally, the boundary region is determined by solving the level set equation for a non-zero level corresponding to a surface at the specified depth from the fluid surface. The set of spray particles inherit an initial state, for example a velocity, from the fluid simulation. Subsequent motion of the spray particles is determined according to a ballistic simulation, rather than a fluid simulation, thereby substantially reducing the computational burden required to animate the fluid. Spray particles that sink below a specified depth from the fluid surface are removed.

Abstract: Light field imaging systems, and in particular light field lenses that can be mated with a variety of conventional cameras (e.g., digital or photographic/film, image and video/movie cameras) to create light field imaging systems. Light field data collected by these light field imaging systems can then be used to produce 2D images, right eye/left eye 3D images, to refocus foreground images and/or background images together or separately (depth of field adjustments), and to move the camera angle, as well as to render and manipulate images using a computer graphics rendering engine and compositing tools.

Abstract: A method for color grading within a component color space associated with a display includes receiving a source image comprising a plurality of pixels, wherein each pixel is associated with a color comprising a plurality of color component values in the component color space, wherein the component color space comprises RGB, and wherein a pixel is associated with a color inside a gamut of the display but outside a gamut of a target media, receiving a color grading signal from a user, modifying the color associated with the pixel from the plurality of pixels in response to the color grading signal, to form a graded image comprising the pixel, wherein the pixel is associated with a graded color comprising a plurality of color component values, displaying the graded image on the display to the user, automatically performing a gamut remapping of the graded color associated with the pixel, to form a gamut remapped image comprising the pixel, wherein the pixel is associated with a gamut remapped color comprising a p

Abstract: A method for a computer system includes opening a model of an object, wherein the model comprises a plurality of geometric elements, determining a subset of geometric elements from the plurality of geometric elements of the model, modifying properties of one or more of the geometric elements in the subset of geometric elements to form a modified subset of geometric elements, and using the modified subset of geometric elements to represent the model of the object in the computer system.

Abstract: A method for invising objects includes receiving information indicating an intersection between a first object and a second object. Visibility of the first object is modified based on the amount of interpenetration between the first object and the second object. A predetermined threshold may be received. The visibility of the first object may be reduced while the amount of the interpenetration fails to exceed the predetermined threshold. The first object may be made invisible when the predetermined threshold is exceeded.

Abstract: A method for a computer system includes determining a plurality of illumination modes associated with a plurality of scene descriptors, wherein the plurality of scene descriptors includes a first scene descriptor and a second scene descriptor, determining a first plurality of weights, wherein each weight from the first plurality of weights is associated with an illumination mode from the plurality of illumination modes, determining illumination data associated with the first scene descriptor in response to the first plurality of weights and in response to the plurality of illumination modes, determining a second plurality of weights, wherein each weight from the second plurality of weights is associated with an illumination mode from the plurality of illumination modes, and determining illumination data associated with the second scene descriptor in response to the second plurality of weights and in response to the plurality of illumination modes.

Abstract: A method for a computer system includes retrieving a plurality of base poses for an object, retrieving a plurality of base texture maps associated with the plurality of base poses, receiving a desired pose for the object, determining a plurality of coefficients associated with the plurality of base poses in response to the desired pose and to the plurality of base poses, and determining a desired texture map in response to the plurality of coefficients and to the plurality of base texture maps.

Abstract: Techniques that give animators the direct control they are accustomed to with key frame animation, while providing for path-based motion. A key frame animation-based interface is used to achieve path-based motion.

Abstract: A computerized method for computing an approximation for irradiance at a point in space from a plurality of distant lights sources includes determining a normal to a surface at a point on the surface being illuminated by the light sources, and determining a direction from the light sources to the point. The method further includes retrieving a function of the normal and the direction wherein the function is configured to provide an approximation of the irradiance, and combining the function with a function of distance, wherein the distance is from the light sources to the point. The method further includes determining an approximation for the irradiance at the point from the combined function with the function of distance based on the normal, the direction, and the distance.

Abstract: A computer-implemented method for generating images. The method includes receiving first and second target images. The method further includes computing a delta image based on a difference between the first target image and the second target image and a technique for multiplexing a first display image with the delta image, where the first display image multiplexed with the delta image, when viewed by a person in an ambient setting, is perceived as the second target image. Advantageously, a hidden image is obscured from an ambient observer, while still providing the ambient observer with a target image that is intended to be perceived.

Abstract: Points can be manipulated through multiple operations with respect to a guide surface using only a single projection operation. A point is projected from its native coordinate system, such as an object space or world space coordinate system, into the parametric space of an unposed guide surface. The projected point is manipulated in the parametric space according to one or more desired operations. The guide surface can be posed to further implement other operations. The guide surface can then be evaluated at the modified parametric space point to determine a corresponding point in the native coordinate system for further manipulation and/or rendering. The manipulation of the point in the parametric space of the guide surface can be expressed through one or more animation variables. The values of multiple animation variables can be used to determine a single operation on the point in parametric space.