Abstract: A method is described that includes receiving, from a first device, input used to select a first object in a computer-generated environment. The first device has at least two degrees of freedom with which to control the selection of the first object. The method also includes removing, in response to the selection of the first object, at least two degrees of freedom previously available to a second device used to manipulating a second object in the computer-generated environment. The removed degrees of freedom correspond to the at least two degrees of freedom of the first device and specify an orientation of the second object relative to the selected first object. Additionally, the method includes receiving, from the second device, input including movements within the reduced degrees of freedom used to manipulate a position of the second object while maintaining the specified orientation relative to the selected first object.

Abstract: Among other disclosed subject matter, a system includes a first camera generating a live image of a scene, the first camera configured for being placed in a plurality of locations by robotic motion. The system includes a handheld device that includes a display device for continuously presenting the live image, wherein movement of the handheld device causes the handheld device to generate an output that controls the robotic motion.

Abstract: A computer-implemented method includes comparing one or more surface features to a motion model. The surface feature or surface features represent a portion of an object in an image. The method also includes identifying a representation of the object from the motion model, based upon the comparison.

Abstract: The present disclosure includes, among other things, systems, methods and program products for generating animation keyframes and a corresponding 3D animation sequence from a plurality of 2D images.

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: The present disclosure includes, among other things, systems, methods and program products for integrating a motion synthesis system into a video game system.

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 identifying one or more convex polygons being adjacent to a virtual object introduced into a virtual scene. The one or more convex polygons define a navigable area within the virtual scene. The method also includes redefining the one or more convex polygons adjacent to the virtual object to adjust the navigable area for the introduction of the virtual object. Redefining the one or more convex polygons uses Boolean operations and allows aligned perimeters of adjacent convex polygons to use unshared vertices.

Abstract: A computer-implemented method includes identifying a representation of a feature of an animated character by inverting a skinned representation of the feature in one position. The inversion includes a non-linear inversion of the skinned representation of the feature. The method also includes skinning the identified feature representation to produce the animated character in another position.

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 system includes a computing device that includes a memory for storing one or more animations (e.g., a first and a second animation), and a model compressor. The model compressor quantifies similarities between the first animation and the second animation, and, groups the first and second animation based upon the quantified similarities. The model compressor is also configured to compress the first animation and the second animation to produce a first model that represents the content of the first animation and the second animation.

Abstract: A system includes a computer system capable of representing one or more animated characters. The computer system includes a blendshape manager that combines multiple blendshapes to produce the animated character. The computer system also includes an expression manager to respectively adjust one or more control parameters associated with each of the plurality of blendshapes for adjusting an expression of the animated character. The computer system also includes a corrective element manager that applies one or more corrective elements to the combined blendshapes based upon at least one of the control parameters. The one or more applied corrective elements are adjustable based upon one or more of the control parameters absent the introduction of one or more additional control parameters.

Abstract: A system includes a computing device that includes a memory for storing content of a sequence of frames, and a frame predictor. The frame predictor determines a difference between content of a first frame and content of a second frame, in which the first and second frames are adjacent in the sequence of frames. The difference between the content of the first and second frames is representative of image changes included in the content of first and second frames. The frame predictor is configured to produce an intermediate frame using at least one of the first and second frames, and the determined difference. The frame predictor is further configured to insert the intermediate frame into the frame sequence.

Abstract: A system includes a computing device that includes a memory for storing instructions. The computing device also includes a processor configured to execute the instructions to perform a method that includes combining, in a nonlinear manner, a first set of vertex displacements that represent the difference between a first animated expression and a neutral animated expression with a second set of vertex displacements that represent the difference between a second animated expression and the neutral animated expression. The number of vertices associated with the first set of vertex displacements of the first animated expression is equivalent to the number of vertices associated with the second set of vertex displacements of the second animated expression.

Abstract: Among other disclosure, a computer-implemented method for retaining a surface detail includes identifying a surface that is to be used for generating an image in a rendering process. The surface includes polygons to be changed from an initial size to a larger size as the surface is changed to a lower resolution as part of tessellating the surface. The surface includes at least one surface detail smaller than the larger polygon size. The method includes storing information corresponding to at least a portion of the surface that includes polygons forming the surface detail. The method includes tesselating the surface, wherein the surface assumes the lower resolution. The method includes determining, while the image is at the lower resolution and using the stored information, a shading sample for at least one of the polygons of the larger size that includes the surface detail. The method includes storing the shading sample.

Abstract: In general, one or more aspects of the subject matter described in this specification can include associating with each clip in a sequence of one or more clips a copy of a three dimensional (3D) scene that was used to create the clip, where the clip is a sequence of one or more images that depict the clip's respective 3D scene from the perspective of one or more virtual cameras. Input identifying a clip in the sequence is received. In response to the receiving, a copy of the identified clip's associated copy of the 3D scene is presented in an editor.

Abstract: A computer-implemented method for adjusting stereo images includes receiving a video sequence associated with a recorded setting of a stereoscopic camera, the video sequence comprising pairs of left and right images. The method includes processing the pairs of left and right images to reduce influence of a discrepancy between the recorded setting and an actual configuration of the stereoscopic camera.

Abstract: A computer-implemented method includes transferring motion information from one or more motion meshes to an animation mesh. The motion mesh represents the motion of surface features of an object. A shape mesh provides a portion of the shape of the object to the animation mesh.

Abstract: Systems and methods are described, which create a mapping from a space of a source object (e.g., source facial expressions) to a space of a target object (e.g., target facial expressions). In certain implementations, the mapping is learned based a training set composed of corresponding shapes (e.g. facial expressions) in each space. The user can create the training set by selecting expressions from, for example, captured source performance data, and by sculpting corresponding target expressions. Additional target shapes (e.g., target facial expressions) can be interpolated and extrapolated from the shapes in the training set to generate corresponding shapes for potential source shapes (e.g., facial expressions).

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are disclosed for animations that simulate skin deformation relative to a muscle. Displacement of a skin representation in response to deformation of a muscle representation and sliding of the skin representation over the deformed muscle representation can be determined quickly and interactively by monitoring changes in position and scale of defining ring elements of the muscle representation's geometry. The determined skin displacements can be constrained to prevent portions of the displaced skin representation from sinking into the underlying muscle representation's geometry.

Abstract: Among other disclosed subject matter, a computer program product is tangibly embodied in a computer-readable storage medium and includes instructions that when executed by a processor perform a method for allocating assets. The method includes assigning each of multiple operation sectors defined by a software program to respective ones of multiple load groups, each load group grouping at least one operation sector for loading assets of the operation sector into memory. The method includes assigning all assets from the multiple operation sectors into respective ones of multiple clusters based on associations between the respective assets and the multiple operation sectors. The method includes generating and storing a memory layout that assigns one of multiple memory locations to each of the multiple clusters for at least one of the multiple load groups.

Abstract: A computer-implemented method for creating a character for an animation includes modifying a first polygonal geometric structure, having a specific form, to generate a second polygonal geometric structure having another form. The first polygonal geometric structure is associated with a definition of multiple points relative to vertices on the first polygonal geometric structure. The method includes transforming the definition, in multiple progressive refinements, to generate a transformed definition for the second polygonal geometric structure. The method includes storing the transformed definition in association with the second polygonal geometric structure, the transformed definition to be used in generating a geometry for the second polygonal geometric structure. A system includes a character component management module, a transforming module and a database.

Abstract: A first input is received in an animation creation application having a user interface showing a virtual-space area for first objects, and a timeline area for second objects representing events. To generate the first input, a user presses and holds an input control while a cursor is over one of the first or second objects. It is determined whether the input control is held for at least a predefined duration. If so, a copy of the object is assigned to the cursor, and the copy is subsequently pasted at another location in the user interface upon the input control ceasing to be held after the cursor is moved to the other location. If the input control does not remain held for at least the predefined duration the copy of the object is not assigned to the cursor.

Abstract: The present disclosure includes, among other things, systems, methods and program products for translating RenderMan shading language code.

Abstract: A computer-implemented method includes identifying a primary node that represents a first pose of an online character. The first pose is associated with a constraint being inactive. The method also includes identifying the primary node representing a second pose of the online character. The second pose is associated with the constraint being active. The method also includes calculating the difference between the primary node of the second pose and the primary node of the first pose. Further, the method includes applying the difference to the primary node of the first pose.

Abstract: A system includes a computing device that includes a memory for storing one or more computer graphics, and a graphics distorter. The graphics distorter applies a distortion model to the computer graphic to produce a distorted version of the computer graphic, while substantially simultaneously allowing user interactions with the computer graphic. The applied distortion model represents lens distortion.

Abstract: A computer-implemented method for simulating a granular material includes removing, from a layer of granular material in a virtual domain defined by a data structure stored in a computer readable storage medium, a portion of the granular material in a closed region where the portion and a part of an object impacting the granular material are defined as occupying a same space. The method includes determining a value for a size aspect of the portion based on applying a numerical solver along an entirety of a boundary of the closed region. The method includes placing additional granular material along the boundary to create a shape resulting from the impact of the object. The method includes generating an image using the data structure, the image reflecting the impact of the object on the granular material in the virtual domain.

Abstract: Among other disclosed subject matter, a computer-implemented method for generating a surface representation of an item includes identifying, for a point on an item in an animation process, at least first and second transformation points corresponding to respective first and second transformations of the point. Each of the first and second transformations represents an influence on a location of the point of respective first and second joints associated with the item. The method includes determining an axis for a cylindrical coordinate system using the first and second transformations. The method includes performing an interpolation of the first and second transformation points in the cylindrical coordinate system to obtain an interpolated point. The method includes recording the interpolated point in a surface representation of the item in the animation process.

Abstract: A computer-implemented method includes identifying a representation of a feature of an animated character by inverting an skinned representation of the feature in one position. The inversion includes a non-linear inversion of the skinned representation of the feature. The method also includes skinning the identified feature representation to produce the animated character in another position.

Abstract: Among other disclosed subject matter, a computer-implemented method for pattern matching includes receiving a pattern image, a mask image and a search image, the mask image having an arbitrary shape and identifying a portion of the pattern image. The method includes evaluating a normalized cross-correlation equation based on the pattern image, the mask image and the search image, including at least a convolution of the mask image and the search image. The method includes outputting a result of evaluating the normalized cross-correlation equation, the result indicating whether the search image matches the portion of the pattern image.

Abstract: A computer-implemented method includes selecting a polygon that includes a convex shape defined by vertices represented by integer coordinates. The method also includes determining a polygon transfer function from cones defined by some of the vertices. The polygon transfer function defines image processing operations independent of the scale of the polygon.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes generating intermediate values from an evaluation of one or more static expressions within shader programming code that is configured to modify an appearance of an image, compressing the intermediate values based on a determination of which intermediate values are duplicative, and storing the compressed intermediate values in a buffer accessible to an image rendering application.

Abstract: A system includes a computing device that includes a memory for storing a three-dimensional model that represents particles of a coarse fire simulation. The computing device also includes a graphics refiner for producing two-dimensional simulation segments from the three-dimensional model that represents particles of a coarse fire simulation. The separation distance between two or more of the two-dimensional simulation segments is based upon a level of spatial detail provided by the coarse fire simulation. The graphics refiner is configured to separately process the two-dimensional simulation segments to produce a detailed fire simulation.

Abstract: In general, one or more aspects of the subject matter described in this specification can include associating with each clip in a sequence of one or more clips a copy of a three dimensional (3D) scene that was used to create the clip, where the clip is a sequence of one or more images that depict the clip's respective 3D scene from the perspective of one or more virtual cameras. Input identifying a clip in the sequence is received. In response to the receiving, a copy of the identified clip's associated copy of the 3D scene is presented in an editor.

Abstract: A computer-implemented method for texturing a modeled surface includes receiving an albedo map corresponding to light scattering under uniform incident diffuse light. The method includes determining, using the albedo map, a local scattering parameter for a multipole bidirectional scattering surface reflectance distribution function (BSSRDF). The method includes texturing a modeled surface using the BSSRDF and the local scattering parameter.

Abstract: The present disclosure includes, among other things, systems, methods and program products for integrating a motion synthesis system into a video game system.

Abstract: A system includes a computer system capable of representing one or more animated characters. The computer system includes a blendshape manager that combines multiple blendshapes to produce the animated character. The computer system also includes an expression manager to respectively adjust one or more control parameters associated with each of the plurality of blendshapes for adjusting an expression of the animated character. The computer system also includes a corrective element manager that applies one or more corrective elements to the combined blendshapes based upon at least one of the control parameters. The one or more applied corrective elements are adjustable based upon one or more of the control parameters absent the introduction of one or more additional control parameters.

Abstract: A computer-implemented method includes selecting a polygon that includes a convex shape defined by vertices represented by integer coordinates. The method also includes determining a polygon transfer function from cones defined by some of the vertices. The polygon transfer function defines image processing operations independent of the scale of the polygon.

Abstract: A computer-implemented method includes comparing content captured during one session and content captured during another session. A surface feature of an object represented in the content of one session corresponds to a surface feature of an object represented in the content of the other session. The method also includes substantially aligning the surface features of the sessions and combining the aligned content.

Abstract: Among other disclosed subject matter, a computer-implemented method for generating a surface representation of an item includes identifying, for a point on an item in an animation process, at least first and second transformation points corresponding to respective first and second transformations of the point. Each of the first and second transformations represents an influence on a location of the point of respective first and second joints associated with the item. The method includes determining an axis for a cylindrical coordinate system using the first and second transformations. The method includes performing an interpolation of the first and second transformation points in the cylindrical coordinate system to obtain an interpolated point. The method includes recording the interpolated point in a surface representation of the item in the animation process.

Abstract: The present disclosure includes, among other things, systems, methods and program products for translating RenderMan shading language code.

Abstract: Among other disclosure, a computer-implemented method for retaining a surface detail includes identifying a surface that is to be used for generating an image in a rendering process. The surface includes polygons to be changed from an initial size to a larger size as the surface is changed to a lower resolution as part of tessellating the surface. The surface includes at least one surface detail smaller than the larger polygon size. The method includes storing information corresponding to at least a portion of the surface that includes polygons forming the surface detail. The method includes tesselating the surface, wherein the surface assumes the lower resolution. The method includes determining, while the image is at the lower resolution and using the stored information, a shading sample for at least one of the polygons of the larger size that includes the surface detail. The method includes storing the shading sample.

Abstract: A computer-implemented method includes selecting a subset of images from a set of captured images. A surface feature of one object is represented in the content of each selected subset image. The method also includes decomposing the surface feature content of each selected image to produce a model of representations of the object.

Abstract: A computer-implemented method includes comparing one or more surface features to a motion model. The surface feature or surface features represent a portion of an object in an image. The method also includes identifying a representation of the object from the motion model, based upon the comparison.

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.

Abstract: A computer-implemented method includes identifying a representation of a feature of an animated character by inverting an skinned representation of the feature in one position. The inversion includes a non-linear inversion of the skinned representation of the feature. The method also includes skinning the identified feature representation to produce the animated character in another position.

Abstract: Systems and methods are described, which create a mapping from a space of a source object (e.g., source facial expressions) to a space of a target object (e.g., target facial expressions). In certain implementations, the mapping is learned based a training set composed of corresponding shapes (e.g. facial expressions) in each space. The user can create the training set by selecting expressions from, for example, captured source performance data, and by sculpting corresponding target expressions. Additional target shapes (e.g., target facial expressions) can be interpolated and extrapolated from the shapes in the training set to generate corresponding shapes for potential source shapes (e.g., facial expressions).

Abstract: In one general aspect, a method is described. The method includes generating a positional relationship between one or more support structures having at least one motion capture mark and at least one virtual structure corresponding to geometry of an object to be tracked and positioning the support structures on the object to be tracked. The support structures has sufficient rigidity that, if there are multiple marks, the marks on each support structure maintain substantially fixed distances from each other in response to movement by the object. The method also includes determining an effective quantity of ray traces between one or more camera views and one or more marks on the support structures, and estimating an orientation of the virtual structure by aligning the determined effective quantity of ray traces with a known configuration of marks on the support structures.

Abstract: A computer-implemented method for texturing a modeled surface includes receiving an albedo map corresponding to light scattering under uniform incident diffuse light. The method includes determining, using the albedo map, a local scattering parameter for a multipole bidirectional scattering surface reflectance distribution function (BSSRDF). The method includes texturing a modeled surface using the BSSRDF and the local scattering parameter.

Abstract: Changes to the outputs of a dependency graph, which has attribute nodes and operator nodes, are detected by forming product proxies for the outputs of dependency graph nodes. The product proxies can be formed by entering information about the dependency graph into a hashing algorithm. Before and after product proxies are then used to determine if the outputs have changed.

Abstract: In one general aspect, a method is described. The method includes generating a positional relationship between one or more support structures having at least one motion capture mark and at least one virtual structure corresponding to geometry of an object to be tracked and positioning the support structures on the object to be tracked. The support structures has sufficient rigidity that, if there are multiple marks, the marks on each support structure maintain substantially fixed distances from each other in response to movement by the object. The method also includes determining an effective quantity of ray traces between one or more camera views and one or more marks on the support structures, and estimating an orientation of the virtual structure by aligning the determined effective quantity of ray traces with a known configuration of marks on the support structures.