Abstract: Systems and methods for displaying a virtual character in a mixed reality environment are disclosed. In some embodiments, a view of the virtual character is based on an animation rig comprising primary joints and helper joints. The animation rig may be in a pose defined by spatial relationships between the primary joints and helper joints. The virtual character may be moving in the mixed reality environment. In some instances, the virtual character may be moving based on a comparison of interestingness values associated with elements in the mixed reality environment. The spatial relationship transformation associated with the movement may be indicated by movement information. In some embodiments, the movement information is received from a neural network.

Abstract: Skinning parameters used to animate a virtual avatar can include mesh weights and joint transforms of a skeleton. Systems and methods are provided for determining skinning parameters using an optimization process subject to constraints based on human-understandable or anatomically-motivated relationships among skeletal joints. Input to the optimization process can include a high-order skeleton and the applied constraints can dynamically change during the optimization. The skinning parameters can be used in linear blend skinning (LBS) applications in augmented reality.

Abstract: Systems and methods for reducing the dimensionality of a blendshape deformation matrix. A plurality of blendshapes can be stored in an input deformation matrix. Principal components of the input deformation matrix can be determined. One or more principal components of the input deformation matrix can be omitted, leaving one or more remaining principal components. An output deformation matrix can be generated using one or more blendshapes associated with the remaining principal component(s).

Abstract: Systems and methods for displaying a virtual character in a mixed reality environment are disclosed. In some embodiments, a view of the virtual character is based on an animation rig comprising primary joints and helper joints. The animation rig may be in a pose defined by spatial relationships between the primary joints and helper joints. The virtual character may be moving in the mixed reality environment. In some instances, the virtual character may be moving based on a comparison of interestingness values associated with elements in the mixed reality environment. The spatial relationship transformation associated with the movement may be indicated by movement information. In some embodiments, the movement information is received from a neural network.

Abstract: Systems and methods for displaying a virtual character in a mixed reality environment are disclosed. In some embodiments, a view of the virtual character is based on an animation rig comprising primary joints and helper joints. The animation rig may be in a pose defined by spatial relationships between the primary joints and helper joints. The virtual character may be moving in the mixed reality environment. In some instances, the virtual character may be moving based on a comparison of interestingness values associated with elements in the mixed reality environment. The spatial relationship transformation associated with the movement may be indicated by movement information. In some embodiments, the movement information is received from a neural network.

Abstract: Systems and methods generating an animation rig corresponding to a pose of a subject include accessing image data corresponding to the pose of the subject. The image data can include the face of the subject. The systems and methods process the image data by successively analyzing subregions of the image according to a solver order. The solver order can be biologically or anatomically ordered to proceed from subregions that cause larger scale movements to subregions that cause smaller scale movements. In each subregion, the systems and methods can perform an optimization technique to fit parameters of the animation rig to the input image data. After all subregions have been processed, the animation rig can be used to animate an avatar to appear to be performing the pose of the subject.

Abstract: Systems and methods for reducing the dimensionality of a blendshape deformation matrix. A plurality of blendshapes can be stored in an input deformation matrix. Principal components of the input deformation matrix can be determined. One or more principal components of the input deformation matrix can be omitted, leaving one or more remaining principal components. An output deformation matrix can be generated using one or more blendshapes associated with the remaining principal component(s).

Abstract: Systems and methods generating an animation rig corresponding to a pose of a subject include accessing image data corresponding to the pose of the subject. The image data can include the face of the subject. The systems and methods process the image data by successively analyzing subregions of the image according to a solver order. The solver order can be biologically or anatomically ordered to proceed from subregions that cause larger scale movements to subregions that cause smaller scale movements. In each subregion, the systems and methods can perform an optimization technique to fit parameters of the animation rig to the input image data. After all subregions have been processed, the animation rig can be used to animate an avatar to appear to be performing the pose of the subject.

Abstract: Systems and methods for using three-dimensional scans of a physical subject to determine positions and/or orientations of skeletal joints in the rigging for a virtual character. At least one articulation segment of a polygon mesh for the virtual character may be determined. The articulation segment may include a subset of vertices in the polygon mesh. An indicator of the position or orientation of the articulation segment of the polygon mesh may be determined. Based on the indicator of the position or orientation of the articulation segment, the position or orientation of at least one joint for deforming the polygon mesh may be determined.

Abstract: Systems and methods for reducing pose space dimensionality. A plurality of example poses can define an input pose space. Each of the example poses can include a set of joint rotations for a virtual character. The joint rotations can be expressed with a singularity-free mathematical representation. The plurality of example poses can then be clustered into one or more clusters. A representative pose can be determined for each cluster. An output pose space with a reduced dimensionality, as compared to the input pose space, can then be provided.

Abstract: Systems and methods for using three-dimensional scans of a physical subject to determine positions and/or orientations of skeletal joints in the rigging for a virtual character. At least one articulation segment of a polygon mesh for the virtual character may be determined. The articulation segment may include a subset of vertices in the polygon mesh. An indicator of the position or orientation of the articulation segment of the polygon mesh may be determined. Based on the indicator of the position or orientation of the articulation segment, the position or orientation of at least one joint for deforming the polygon mesh may be determined.

Abstract: Systems and methods for displaying a virtual character in a mixed reality environment are disclosed. In some embodiments, a view of the virtual character is based on an animation rig comprising primary joints and helper joints. The animation rig may be in a pose defined by spatial relationships between the primary joints and helper joints. The virtual character may be moving in the mixed reality environment. In some instances, the virtual character may be moving based on a comparison of interestingness values associated with elements in the mixed reality environment. The spatial relationship transformation associated with the movement may be indicated by movement information. In some embodiments, the movement information is received from a neural network.

Abstract: Examples of systems and methods for matching a base mesh to a target mesh for a virtual avatar or object are disclosed. The systems and methods may be configured to automatically match a base mesh of an animation rig to a target mesh, which may represent a particular pose of the virtual avatar or object. Base meshes may be obtained by manipulating an avatar or object into a particular pose, while target meshes may be obtain by scanning, photographing, or otherwise obtaining information about a person or object in the particular pose. The systems and methods may automatically match a base mesh to a target mesh using rigid transformations in regions of higher error and non-rigid deformations in regions of lower error.

Abstract: Systems and methods for displaying a virtual character in a mixed reality environment are disclosed. In some embodiments, a view of the virtual character is based on an animation rig comprising primary joints and helper joints. The animation rig may be in a pose defined by spatial relationships between the primary joints and helper joints. The virtual character may be moving in the mixed reality environment. In some instances, the virtual character may be moving based on a comparison of interestingness values associated with elements in the mixed reality environment. The spatial relationship transformation associated with the movement may be indicated by movement information. In some embodiments, the movement information is received from a neural network.

Abstract: Systems and methods for reducing pose space dimensionality. A plurality of example poses can define an input pose space. Each of the example poses can include a set of joint rotations for a virtual character. The joint rotations can be expressed with a singularity-free mathematical representation. The plurality of example poses can then be clustered into one or more clusters. A representative pose can be determined for each cluster. An output pose space with a reduced dimensionality, as compared to the input pose space, can then be provided.

Abstract: Examples of systems and methods for matching a base mesh to a target mesh for a virtual avatar or object are disclosed. The systems and methods may be configured to automatically match a base mesh of an animation rig to a target mesh, which may represent a particular pose of the virtual avatar or object. Base meshes may be obtained by manipulating an avatar or object into a particular pose, while target meshes may be obtain by scanning, photographing, or otherwise obtaining information about a person or object in the particular pose. The systems and methods may automatically match a base mesh to a target mesh using rigid transformations in regions of higher error and non-rigid deformations in regions of lower error.

Abstract: Skinning parameters used to animate a virtual avatar can include mesh weights and joint transforms of a skeleton. Systems and methods are provided for determining skinning parameters using an optimization process subject to constraints based on human-understandable or anatomically-motivated relationships among skeletal joints. Input to the optimization process can include a high-order skeleton and the applied constraints can dynamically change during the optimization. The skinning parameters can be used in linear blend skinning (LBS) applications in augmented reality.

Abstract: Systems and methods for reducing pose space dimensionality. A plurality of example poses can define an input pose space. Each of the example poses can include a set of joint rotations for a virtual character. The joint rotations can be expressed with a singularity-free mathematical representation. The plurality of example poses can then be clustered into one or more clusters. A representative pose can be determined for each cluster. An output pose space with a reduced dimensionality, as compared to the input pose space, can then be provided.

Abstract: Systems and methods generating an animation rig corresponding to a pose of a subject include accessing image data corresponding to the pose of the subject. The image data can include the face of the subject. The systems and methods process the image data by successively analyzing subregions of the image according to a solver order. The solver order can be biologically or anatomically ordered to proceed from subregions that cause larger scale movements to subregions that cause smaller scale movements. In each subregion, the systems and methods can perform an optimization technique to fit parameters of the animation rig to the input image data. After all subregions have been processed, the animation rig can be used to animate an avatar to appear to be performing the pose of the subject.

Abstract: Skinning parameters used to animate a virtual avatar can include mesh weights and joint transforms of a skeleton. Systems and methods are provided for determining skinning parameters using an optimization process subject to constraints based on human-understandable or anatomically-motivated relationships among skeletal joints. Input to the optimization process can include a high-order skeleton and the applied constraints can dynamically change during the optimization. The skinning parameters can be used in linear blend skinning (LBS) applications in augmented reality.