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: 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: A method of compressing a deep image representation may include receiving a deep image, where the deep image may include multiple pixels, and where each pixel in the deep image may include multiple samples. The method may also include compressing the deep image by combining samples in each pixel that are associated with the same primitives. This process may be repeated on a pixel-by-pixel basis. Some embodiments may use primitive IDs to match pixels to primitives through the rendering and compositing process.

Abstract: A computer-implemented method for handling a modification of an animation having a constraint includes detecting a user modification of an animation that involves at least first and second objects, the first object constrained to the second object during a constrained period and non-constrained to the second object during a non-constrained period. The method includes, based on the user modification, selecting one of at least first and second compensation adjustments for the animation based on a compensation policy; and adjusting the animation according to the selected compensation adjustment.

Abstract: An apparatus is disclosed which may serve as a target for calibrating a camera. The apparatus comprises one or more planar surfaces. The apparatus includes at least one fiducial marking on a planar surface. The set of all planar markings on the apparatus are distinguishable.

Abstract: Methods and systems are disclosed for calibrating a camera using a calibration target apparatus that contains at least one fiducial marking on a planar surface. The set of all planar markings on the apparatus are distinguishable. Parameters of the camera are inferred from at least one image of the calibration target apparatus. In some embodiments, pixel coordinates of identified fiducial markings in an image are used with geometric knowledge of the apparatus to calculate camera parameters.

Abstract: This document describes systems and techniques for representing computer-generated objects with a limit mesh. In general, the systems and techniques may generate an object's form or appearance based on an estimation of how the object would look if shapes that form the object were infinitely subdivided to create a smooth surface for the object. For example, when a user views a distance object in a video game, its shape can be estimated by calculating an approximation of what the object would look like if the polygons that make up the object were infinitely divided. As the user approaches the object, curving solutions that may be embedded in the object can be used to construct curves for the object so that it appears smooth.

Abstract: A system includes a visual data collector for collecting visual information from an image of one or more features of an object. The system also includes a physical data collector for collecting sensor information provided by at one or more sensors attached to the object. The system also includes a computer system that includes a motion data combiner for combining the visual information the sensor information. The motion data combiner is configured to determine the position of a representation of one or more of the feature in a virtual representation of the object from the combined visual information and sensor information. Various types of virtual representations may be provided from the combined information, for example, one or more poses (e.g., position and orientation) of the object may be represented.

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: An animation rig is displayed in a plurality of reference poses. The animation rig has a pose deformation in each pose. A refinement deformation for each reference pose is received. Each refinement deformation is mapped to a respective point in n-dimensional space. A complex is built in the n-dimensional space. The complex includes a mesh of simplices, each corner of each simplex associated with one of the deformations.

Abstract: In one aspect, a method is performed by one or more processors. The method includes receiving a primary view image showing a scene from a view of a primary camera; depth values for one or more objects in the scene; and a camera offset between the primary camera and a secondary camera. The method further includes determining disparities for each pixel in the primary view image. The method further includes generating a secondary view image using the primary view image, the depth values, and the camera offset. At least some of the pixels are repositioned according to the determined disparities.

Abstract: A method of applying a post-render motion blur to an object may include receiving a first image of the object. The first image need not be motion blurred, and the first image may include a first pixel and rendered color information for the first pixel. The method may also include receiving a second image of the object. The second image may be motion blurred, and the second image may include a second pixel and a location of the second pixel before the second image was motion blurred. Areas that are occluded in the second image may be identified and colored using a third image rendering only those areas. Unoccluded areas of the second image may be colored using information from the first image.

Abstract: Systems and techniques for dynamically capturing and reconstructing lighting are provided. The systems and techniques may be based on a stream of images capturing the lighting within an environment as a scene is shot. Reconstructed lighting data may be used to illuminate a character in a computer-generated environment as the scene is shot. For example, a method may include receiving a stream of images representing lighting of a physical environment. The method may further include compressing the stream of images to reduce an amount of data used in reconstructing the lighting of the physical environment and may further include outputting the compressed stream of images for reconstructing the lighting of the physical environment using the compressed stream, the reconstructed lighting being used to render a computer-generated environment.

Abstract: A virtual director's viewfinder includes: a housing with a form factor of a director's viewfinder; at least one mechanical viewfinder control connected to the housing, the virtual director's viewfinder encoding a setting of the mechanical viewfinder control into digital setting information; at least one communication device for communication of the digital setting information to a computer system, and for receiving from the computer system an image generated using the digital setting information; and a display device that presents at least the image received from the computer 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 frames included in series of frames that represent a portion of an animated character. The identified one or more frames can be reconstructed from a portion of the series of frames absent the identified one or more frames. The method also includes removing the identified one or more frames from the series of frames to produce a reduced series of frames, and, transforming the reduced series of frames to produce an animation model that is capable of reconstructing the series of frames for an interactive virtual environment.

Abstract: A device includes a plurality of vertically aligned pairs of light sources. The device is configured to sequentially illuminate the vertically aligned pairs of light sources. The output illuminating can be captured by a camera having a rolling shutter delay to create an image having a rolling shutter artifact. The image can be analyzed to determine the rolling shutter delay of the camera.

Abstract: The present disclosure includes, among other things, systems, methods, and program products for estimating radiant exitance due to subsurface scattering. For example, one or more aspects of the subject matter described in this disclosure can be embodied in one or more methods that include distributing a plurality of sample points across the surface of a 3D object model to be rendered into a 2D image and determining a solid angle subtended by a first sample point and a second sample point relative to a region on the 3D object model. Depending on the determined solid angle relative to a threshold value, a previously determined subsurface scattering contribution for the region or a newly determined subsurface scattering contribution for the region may selectively be used for rendering a portion of the 2D image.

Abstract: Visually representing a composite graph of image functions includes providing a visual representation of a composite graph for an image, the visual representation including first items corresponding to respective image functions, and second items corresponding to containers for image functions, the image to be rendered by performing the image functions in an order defined by the composite graph. The user selects an expansion mode for presenting contents of a first container, each of the containers having a first expansion mode wherein the contents are displayed generally adjacent the visual representation, and a second expansion mode where the contents are displayed generally within the visual representation. A modified visual representation of the composite graph is provided in response to the input, wherein the modified visual representation maintains the order of the image functions defined by the composite graph and has the first container expanded according to the selected expansion mode.

Abstract: Among other aspects, on computer-implemented method includes: receiving at least one command in a computer system from a handheld device; positioning a virtual camera and controlling a virtual scene according to the command; and in response to the command, generating an output to the handheld device for displaying a view of the virtual scene as controlled on a display of the handheld device, the view captured by the virtual camera as positioned.

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 defining at least one of a location in a virtual scene and a time represented in a timeline as being associated with a performance of an animated character. The method also includes aggregating data that represents actions of the animation character for at least one of the defined location and the defined time. The method also includes presenting a user interface that includes a representation of the aggregated actions. The representation is editable to adjust at least one action included in the aggregation.