Abstract: Some implementations of the disclosure are directed to techniques for facial reconstruction from a sparse set of facial markers. In one implementation, a method comprises: obtaining data comprising a captured facial performance of a subject with a plurality of facial markers; determining a three-dimensional (3D) bundle corresponding to each of the plurality of facial markers of the captured facial performance; using at least the determined 3D bundles to retrieve, from a facial dataset comprising a plurality of facial shapes of the subject, a local geometric shape corresponding to each of the plurality of the facial markers; and merging the retrieved local geometric shapes to create a facial reconstruction of the subject for the captured facial performance.

Abstract: A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor configured to execute the instructions to perform a method that includes receiving multiple representations of one or more expressions of an object. Each of the representations includes position information attained from one or more images of the object. The method also includes producing an animation model from one or more groups of controls that respectively define each of the one or more expressions of the object as provided by the multiple representations. Each control of each group of controls has an adjustable value that defines the geometry of at least one shape of a portion of the respective expression of the object. Producing the animation model includes producing one or more corrective shapes if the animation model is incapable of accurately presenting the one or more expressions of the object as provided by the multiple representations.

Abstract: Systems, devices, and methods are disclosed for UV packing. The system includes a non-transitory computer-readable medium operatively coupled to processors. The non-transitory computer-readable medium stores instructions that, when executed, cause the processors to perform a number of operations. One operation is to present a packing map using a graphical user interface including a selection tool. Another operation is to present a first set of one or more target objects using the graphical user interface. Individual ones of the first set include one or more features. One operation is to receive a first user input. Another operation is to, based on the first user input and the one or more features corresponding to the individual ones of the first set, pack the first set into a packing map.

Abstract: Implementations of the disclosure describe systems and methods that leverage machine learning to automate the process of creating music and effects mixes from original sound mixes including domestic dialogue. In some implementations, a method includes: receiving a sound mix including human dialogue; extracting metadata from the sound mix, where the extracted metadata categorizes the sound mix; extracting content feature data from the sound mix, the extracted content feature data including an identification of the human dialogue and instances or times the human dialogue occurs within the sound mix; automatically calculating, with a trained model, content feature data of a music and effects (M&E) sound mix using at least the extracted metadata and the extracted content feature data of the sound mix; and deriving the M&E sound mix using at least the calculated content feature data.

Abstract: Implementations of the disclosure are directed to generating shadows in the physical world that correspond to virtual objects displayed on MR displays. In some implementations, a method includes: synchronously presenting a version of a scene on each of a MR display system and a projector display system, where during presentation: the MR display system displays a virtual object overlaid over a view of a physical environment; and a projector of the projector display system creates a shadow on a surface in the physical environment, the created shadow corresponding to the virtual object displayed by the MR display. In some implementations, the method includes: loading in a memory of the MR display system, a first version of the scene including the virtual object; and loading in a memory of the projector display system a second version of the scene including a virtual surface onto which the virtual object casts a shadow.

Abstract: Some implementations of the disclosure are directed to a pipeline that enables real time engines such as gaming engines to leverage high quality simulations generated offline via film grade simulation systems. In one implementation, a method includes: obtaining simulation data and skeletal mesh data of a character, the simulation data and skeletal mesh data including the character in the same rest pose; importing the skeletal mesh data into a real-time rendering engine; and using at least the simulation data and the imported skeletal mesh data to derive from the simulation data a transformed simulation vertex cache that is usable by the real-time rendering engine during runtime to be skinned in place of the rest pose.

Abstract: Embodiments of the disclosure provide systems and methods for motion capture to generate content (e.g., motion pictures, television programming, videos, etc.). An actor or other performing being can have multiple markers on his or her face that are essentially invisible to the human eye, but that can be clearly captured by camera systems of the present disclosure. Embodiments can capture the performance using two different camera systems, each of which can observe the same performance but capture different images of that performance. For instance, a first camera system can capture the performance within a first light wavelength spectrum (e.g., visible light spectrum), and a second camera system can simultaneously capture the performance in a second light wavelength spectrum different from the first spectrum (e.g., invisible light spectrum such as the IR light spectrum). The images captured by the first and second camera systems can be combined to generate content.

Abstract: An immersive content presentation system can capture the motion or position of a performer in a real-world environment. A game engine can be modified to receive the position or motion of the performer and identify predetermined gestures or positions that can be used to trigger actions in a 3-D virtual environment, such as generating a digital effect, transitioning virtual assets through an animation graph, adding new objects, and so forth. The use of the 3-D environment can be rendered and composited views can be generated. Information for constructing the composited views can be streamed to numerous display devices in many different physical locations using a customized communication protocol. Multiple real-world performers can interact with virtual objects through the game engine in a shared mixed-reality experience.

Abstract: A method of transferring a facial expression from a subject to a computer generated character that includes: receiving a plate with an image of the subject's facial expression and an estimate of intrinsic parameters of a camera used to film the plate; generating a three-dimensional parameterized deformable model of the subject's face where different facial expressions of the subject can be obtained by varying values of the model parameters; solving for the facial expression in the plate by executing a deformation solver to solve for at least some parameters of the deformable model with a differentiable renderer and shape-from-shading techniques, using as inputs, the three-dimensional parameterized deformable model, estimated intrinsic camera parameters, estimated lighting conditions and albedo estimates over a series of iterations to infer geometry of the facial expression and generate an intermediate facial; generating, from the intermediate facial mesh, refined albedo estimates for the deformable model; and

Abstract: A method of transferring a facial expression from a subject to a computer generated character that includes receiving a plate with an image of the subject's facial expression, a three-dimensional parameterized deformable model of the subject's face where different facial expressions of the subject can be obtained by varying values of the model parameters, a model of a camera rig used to capture the plate, and a virtual lighting model that estimates lighting conditions when the image on the plate was captured.

Abstract: Embodiments of the disclosure provide systems and methods for motion capture to generate content (e.g., motion pictures, television programming, videos, etc.). An actor or other performing being can have multiple markers on his or her face that are essentially invisible to the human eye, but that can be clearly captured by camera systems of the present disclosure. Embodiments can capture the performance using two different camera systems, each of which can observe the same performance but capture different images of that performance. For instance, a first camera system can capture the performance within a first light wavelength spectrum (e.g., visible light spectrum), and a second camera system can simultaneously capture the performance in a second light wavelength spectrum different from the first spectrum (e.g., invisible light spectrum such as the IR light spectrum). The images captured by the first and second camera systems can be combined to generate content.

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: Implementations of the disclosure are directed to generating shadows in the physical world that correspond to virtual objects displayed on MR displays. In some implementations, a method includes: synchronously presenting a version of a scene on each of a MR display system and a projector display system, where during presentation: the MR display system displays a virtual object overlaid over a view of a physical environment; and a projector of the projector display system creates a shadow on a surface in the physical environment, the created shadow corresponding to the virtual object displayed by the MR display. In some implementations, the method includes: loading in a memory of the MR display system, a first version of the scene including the virtual object; and loading in a memory of the projector display system a second version of the scene including a virtual surface onto which the virtual object casts a shadow.

Abstract: A system and method for controlling a view of a virtual reality (VR) environment via a computing device with a touch sensitive surface are disclosed. In some examples, a user may be enabled to augment the view of the VR environment by providing finger gestures to the touch sensitive surface. In one example, the user is enabled to call up a menu in the view of the VR environment. In one example, the user is enabled to switch the view of the VR environment displayed on a device associated with another user to a new location within the VR environment. In some examples, the user may be enabled to use the computing device to control a virtual camera within the VR environment and have various information regarding one or more aspects of the virtual camera displayed in the view of the VR environment presented to the user.

Abstract: Views of a virtual environment can be displayed on mobile devices in a real-world environment simultaneously for multiple users. The users can operate selections devices in the real-world environment that interact with objects in the virtual environment. Virtual characters and objects can be moved and manipulated using selection shapes. A graphical interface can be instantiated and rendered as part of the virtual environment. Virtual cameras and screens can also be instantiated to created storyboards, backdrops, and animated sequences of the virtual environment. These immersive experiences with the virtual environment can be used to generate content for users and for feature films.

Abstract: Embodiments of the disclosure provide systems and methods for motion capture to generate content (e.g., motion pictures, television programming, videos, etc.). An actor or other performing being can have multiple markers on his or her face that are essentially invisible to the human eye, but that can be clearly captured by camera systems of the present disclosure. Embodiments can capture the performance using two different camera systems, each of which can observe the same performance but capture different images of that performance. For instance, a first camera system can capture the performance within a first light wavelength spectrum (e.g., visible light spectrum), and a second camera system can simultaneously capture the performance in a second light wavelength spectrum different from the first spectrum (e.g., invisible light spectrum such as the IR light spectrum). The images captured by the first and second camera systems can be combined to generate content.

Abstract: A method may include capturing a first image of a physical environment using a mobile device. The mobile device may include a physical camera and a display. The method may also include receiving a second image from a content provider system. The second image may be generated by the content provider system by rendering a view from a virtual camera in a virtual environment. The virtual environment may represent at least a portion of the physical environment. A location of the virtual camera in the virtual environment may correspond to a location of the physical camera in the physical environment. The second image may include a view of a computer-generated object. The method may additionally include generating a third image by compositing the first image and the second image, and causing the third image to be displayed on the display of the mobile device.

Abstract: An immersive content presentation system and techniques that can detect and correct lighting artifacts caused by movements of one or more taking camera in a performance area consisting of multiple displays (e.g., LED or LCD displays). The techniques include capturing, with a camera, a plurality of images of a performer performing in a performance area at least partially surrounded by one or more displays presenting images of a virtual environment. Where the images of the virtual environment within a frustum of the camera are updated on the one or more displays based on movement of the camera, and images of the virtual environment outside of the frustum of the camera are not updated based on movement of the camera. The techniques further include generating content based on the plurality of captured images.

Abstract: An immersive content presentation system and techniques that can detect and correct lighting artifacts caused by movements of one or more taking camera in a performance area consisting of multiple displays (e.g., LED or LCD displays). The techniques include capturing, with a camera, a plurality of images of a performer performing in a performance area at least partially surrounded by one or more displays presenting images of a virtual environment. Where the images of the virtual environment within a frustum of the camera are updated on the one or more displays based on movement of the camera, and images of the virtual environment outside of the frustum of the camera are not updated based on movement of the camera. The techniques further include generating content based on the plurality of captured images.

Abstract: A system and method for controlling a view of a virtual reality (VR) environment via a computing device with a touch sensitive surface are disclosed. In some examples, a user may be enabled to augment the view of the VR environment by providing finger gestures to the touch sensitive surface. In one example, the user is enabled to call up a menu in the view of the VR environment. In one example, the user is enabled to switch the view of the VR environment displayed on a device associated with another user to a new location within the VR environment. In some examples, the user may be enabled to use the computing device to control a virtual camera within the VR environment and have various information regarding one or more aspects of the virtual camera displayed in the view of the VR environment presented to the user.

Abstract: Systems and techniques are provided for switching between different modes of a media content item. A media content item may include a movie that has different modes, such as a cinematic mode and an interactive mode. For example, a movie may be presented in a cinematic mode that does not allow certain user interactions with the movie. The movie may be switched to an interactive mode during any point of the movie, allowing a viewer to interact with various aspects of the movie. The movie may be displayed using different formats and resolutions depending on which mode the movie is being presented.

Abstract: Systems and techniques are provided for switching between different modes of a media content item. A media content item may include a movie that has different modes, such as a cinematic mode and an interactive mode. For example, a movie may be presented in a cinematic mode that does not allow certain user interactions with the movie. The movie may be switched to an interactive mode during any point of the movie, allowing a viewer to interact with various aspects of the movie. The movie may be displayed using different formats and resolutions depending on which mode the movie is being presented.

Abstract: Views of a virtual environment can be displayed on mobile devices in a real-world environment simultaneously for multiple users. The users can operate selections devices in the real-world environment that interact with objects in the virtual environment. Virtual characters and objects can be moved and manipulated using selection shapes. A graphical interface can be instantiated and rendered as part of the virtual environment. Virtual cameras and screens can also be instantiated to created storyboards, backdrops, and animated sequences of the virtual environment. These immersive experiences with the virtual environment can be used to generate content for users and for feature films.

Abstract: Views of a virtual environment can be displayed on mobile devices in a real-world environment simultaneously for multiple users. The users can operate selections devices in the real-world environment that interact with objects in the virtual environment. Virtual characters and objects can be moved and manipulated using selection shapes. A graphical interface can be instantiated and rendered as part of the virtual environment. Virtual cameras and screens can also be instantiated to created storyboards, backdrops, and animated sequences of the virtual environment. These immersive experiences with the virtual environment can be used to generate content for users and for feature films.

Abstract: A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor configured to execute the instructions to perform a method that includes receiving multiple representations of an object. Each of the representations includes position information of the object and corresponds to an instance in time. For at least one of the representations, the method includes defining a contour that represents a movable silhouette of a surface feature of the object. The method also includes producing a deformable model of the surface of the object from the defined contour and from the at least one representation of the object.

Abstract: A method may include causing first content to be displayed on a display device. The method may also include determining a location of a mobile device relative to the display device. In some embodiments, the mobile device may be positioned such that the first content is visible to a viewer of the mobile device. The method may additionally include causing second content to be displayed on the mobile device such that the second content is layered over the first content.

Abstract: A system and method facilitating a user to manipulate a virtual reality (VR) environment are disclosed. The user may provide an input via a touch sensitive surface of a computing device associated with the user to bind a virtual object in the VR environment to the computing device. The user may then move and/or rotate the computing device to cause the bound virtual object to move and/or rotate in the VR environment accordingly. In some examples, the bound virtual object may cast a ray into the VR environment. The movement and/or rotation of the virtual object controlled by the computing device in those examples can change the direction of the ray. In some examples, the virtual object may include a virtual camera. In those examples, the user may move and/or rotate the virtual camera in the VR environment by moving and/or rotate the computing device.

Abstract: A multi-channel tracking pattern is provided along with techniques and systems for performing motion capture using the multi-channel tracking pattern. The multi-channel tracking pattern includes a plurality of shapes having different colors on different portions of the pattern. The portions with the unique shapes and colors allow a motion capture system to track motion of an object bearing the pattern across a plurality of video frames.

Abstract: Views of a virtual environment can be displayed on mobile devices in a real-world environment simultaneously for multiple users. The users can operate selections devices in the real-world environment that interact with objects in the virtual environment. Virtual characters and objects can be moved and manipulated using selection shapes. A graphical interface can be instantiated and rendered as part of the virtual environment. Virtual cameras and screens can also be instantiated to created storyboards, backdrops, and animated sequences of the virtual environment. These immersive experiences with the virtual environment can be used to generate content for users and for feature films.

Abstract: A method of generating unrecorded camera views may include receiving a plurality of 2-D video sequences of a subject in a real 3-D space, where each 2-D video sequence may depict the subject from a different perspective. The method may also include generating a 3-D representation of the subject in a virtual 3-D space, where a geometry and texture of the 3-D representation may be generated based on the 2D video sequences, and the motion of the 3-D representation in the virtual 3-D space is based on motion of the subject in the real 3-D space. The method may additionally include generating a 2-D video sequence of the motion of the 3D representation using a virtual camera in the virtual 3-D space where the perspective of the virtual camera may be different than the perspectives of the plurality of 2-D video sequences.

Abstract: Embodiments of the disclosure provide systems and methods for motion capture to generate content (e.g., motion pictures, television programming, videos, etc.). An actor or other performing being can have multiple markers on his or her face that are essentially invisible to the human eye, but that can be clearly captured by camera systems of the present disclosure. Embodiments can capture the performance using two different camera systems, each of which can observe the same performance but capture different images of that performance. For instance, a first camera system can capture the performance within a first light wavelength spectrum (e.g., visible light spectrum), and a second camera system can simultaneously capture the performance in a second light wavelength spectrum different from the first spectrum (e.g., invisible light spectrum such as the IR light spectrum). The images captured by the first and second camera systems can be combined to generate content.

Abstract: Embodiments of the disclosure provide systems and methods for motion capture to generate content (e.g., motion pictures, television programming, videos, etc.). An actor or other performing being can have multiple markers on his or her face that are essentially invisible to the human eye, but that can be clearly captured by camera systems of the present disclosure. Embodiments can capture the performance using two different camera systems, each of which can observe the same performance but capture different images of that performance. For instance, a first camera system can capture the performance within a first light wavelength spectrum (e.g., visible light spectrum), and a second camera system can simultaneously capture the performance in a second light wavelength spectrum different from the first spectrum (e.g., invisible light spectrum such as the IR light spectrum). The images captured by the first and second camera systems can be combined to generate content.

Abstract: A system includes a computing device that includes a memory and a processor configured to execute instructions to perform a method that includes receiving multiple representations of one or more expressions of an object. Each representation includes position information attained from one or more images of the object. The method also includes producing an animation model from one or more groups of controls that respectively define each of the one or more expressions of the object as provided by the multiple representations. Each control of each group of controls has an adjustable value that defines the geometry of at least one shape of a portion of the respective expression of the object. Producing the animation model includes producing one or more corrective shapes if the animation model is incapable of accurately presenting the one or more expressions of the object as provided by the multiple representations.

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: Performance capture systems and techniques are provided for capturing a performance of a subject and reproducing an animated performance that tracks the subject's performance. For example, systems and techniques are provided for determining control values for controlling an animation model to define features of a computer-generated representation of a subject based on the performance. A method may include obtaining input data corresponding to a pose performed by the subject, the input data including position information defining positions on a face of the subject. The method may further include obtaining an animation model for the subject that includes adjustable controls that control the animation model to define facial features of the computer-generated representation of the face, and matching one or more of the positions on the face with one or more corresponding positions on the animation model.

Abstract: A handheld device includes: an input control configured to control and modify a virtual scene including a virtual camera; and a display that shows a representation of the controlled and modified virtual scene generated by the virtual camera. A system includes: a computer system configured to execute program instructions for generating a virtual scene including a virtual camera; and handheld device configured to communicate with the computer system for controlling and modifying the virtual scene, the handheld device comprising: an input control configured to control and modify the virtual scene; and a display that shows a representation of the controlled and modified virtual scene generated by the virtual camera.

Abstract: System and methods are provided for a non-coherent point tracking process that allows unknown camera motion to be estimated. One or more edges can be identified in images captured by a camera when shooting a scene. For each of the identified edge in the images, at least one tracking object can be placed arbitrarily on the edge. The positions of tracking objects in the images can then be used to estimate a camera motion. In some embodiments, two tracking objects can be placed arbitrarily on the edge to represent the edge and move along the edge arbitrarily from image to image where the edge appears. Multiple of such edges can be identified in the images and camera motions in multiple directions can be estimated based on the identified edges and combined to obtain a combined camera motion indicating the camera's movement in a 3D space when shooting the scene.

Abstract: A method may include rendering a first view of a three-dimensional (3-D) virtual scene comprising a view of first content being displayed on a virtual display device from a location in the 3-D virtual scene. The method may also include rendering a second view comprising one or more content objects. The second view may be rendered from the location in the 3-D virtual scene, and the second scene may include a view of the display device as would be seen through a pair of augmented-reality glasses that display the one or more content objects. The method may additionally include generating a composite view by combing the first view and the second view. The method may further include causing the composite view to be displayed on a virtual-reality headset.

Abstract: In some embodiments a method of transferring facial expressions from a subject to a computer-generated character is provided where the method includes receiving positional information from a motion capture session of the subject representing a performance having facial expressions to be transferred to the computer-generated character, receiving a first animation model that represents the subject, and receiving a second animation model that represents the computer-generated character. Each of the first and second animation models can include a plurality of adjustable controls that define geometries of the model and that can be adjusted to present different facial expressions on the model, and where the first and second animation models are designed so that setting the same values for the same set of adjustable controls in each model generates a similar facial poses on the models.

Abstract: Systems and techniques are provided for transferring changes in animation data between geometric models of a character having different resolutions. For example, systems and techniques are provided for transferring changes in geometric properties between the geometric models. A method may include obtaining a first geometric model of the character and a second geometric model of the character, the geometric models having different resolutions with different numbers of data points. The method may further include determining one or more correspondences between data points of the first geometric model and data points of the second geometric model. The correspondences include one or more data points of the first geometric model that overlap with one or more data points of the second geometric model.

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: Methods and systems efficiently apply known distortion, such as of a camera and lens, to source image data to produce data of an output image with the distortion. In an embodiment, an output image field is segmented into regions so that on each segment the distortion function is approximately linear, and segmentation data is stored in a quadtree. The distortion function is applied to the segmented image field to produce a segmented rendered distortion image (SRDI) and a corresponding look-up table. To distort a source image, a location in the output image field is selected, and the uniquely colored segment at the same location in the SRDI is found. The look-up table provides the local linear inverse of the distortion function, which is applied to determine from where in the source image to take image texture data for the distorted output image.

Abstract: Methods, systems and computer program products pertaining to simulating liquid bodies are presented. The subject matter of this document can be embodied in a method that includes obtaining one or more data arrays representing low frequency spatial features of a simulated volume of liquid, and up-sampling the one or more data arrays to produce corresponding high resolution data arrays. The method also includes obtaining procedural data representing high frequency spatial features of a simulated liquid surface, and modifying the one or more high resolution data arrays using the procedural data to produce corresponding modified data arrays that reflect both the high frequency and the low frequency spatial features of the simulated volume of liquid.

Abstract: A method of motion capture may include accessing a 3D model of a subject, and associating the 3D model of the subject with a 2D representation of the subject in a plurality of frames. The method may also include identifying a change to the 2D representation of the subject between two or more of the plurality of frames, and deforming the 3D model in a virtual 3D space. In some embodiments, the deforming may be based on the identified change to the 2D representation and at least one constraint restricting how the 3D model can be deformed.

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 method may include presenting a scene from linear content on one or more display devices in an immersive environment, and receiving, from a user within the immersive environment, input to change an aspect of the scene. The method may also include accessing 3-D virtual scene information previously used to render the scene, and changing the 3-D virtual scene information according to the changed aspect of the scene. The method may additionally include rending the 3-D virtual scene to incorporate the changed aspect, and presenting the rendered scene in real time in the immersive user environment.

Abstract: A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor configured to execute the instructions to perform a method that includes receiving multiple representations of an object. Each of the representations includes position information of the object and corresponds to an instance in time. For at least one of the representations, the method includes defining a contour that represents a movable silhouette of a surface feature of the object. The method also includes producing a deformable model of the surface of the object from the defined contour and from the at least one representation of the object.

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: An animation analyzer is configured to receive an animation sequence and to identify a subsample of the frames that are to be rendered. A rendering engine is configured to render the subsample of the frames. The rendering engine is further configured to identify the frames that have not been rendered and to generate in-betweens for the frames that have not been rendered. The rendering engine is further configured to assemble the subsample of frames and the in-betweens into a video sequence depicting the animation sequence.