Abstract: Techniques for facial expression capture for character animation are described. In one or more implementations, facial key points are identified in a series of images. Each image, in the series of images, is normalized from the identified facial key points. Facial features are determined from each of the normalized images. Then a facial expression is classified, based on the determined facial features, for each of the normalized images. In additional implementations, a series of images are captured that include performances of one or more facial expressions. The facial expressions in each image of the series of images are classified by a facial expression classifier. Then the facial expression classifications are used by a character animator system to produce a series of animated images of an animated character that include animated facial expressions that are associated with the facial expression classification of the corresponding image in the series of images.

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure facades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

Abstract: Systems and methods for local augmented reality (AR) tracking of an AR object are disclosed. In one example embodiment a device captures a series of video image frames. A user input is received at the device associating a first portion of a first image of the video image frames with an AR sticker object and a target. A first target template is generated to track the target across frames of the video image frames. In some embodiments, global tracking based on a determination that the target is outside a boundary area is used. The global tracking comprises using a global tracking template for tracking movement in the video image frames captured following the determination that the target is outside the boundary area. When the global tracking determines that the target is within the boundary area, local tracking is resumed along with presentation of the AR sticker object on an output display of the device.

Abstract: Systems and methods are disclosed herein for 3-Dimensional portrait reconstruction from a single photo. A face portion of a person depicted in a portrait photo is detected and a 3-Dimensional model of the person depicted in the portrait photo constructed. In one embodiment, constructing the 3-Dimensional model involves fitting hair portions of the portrait photo to one or more helices. In another embodiment, constructing the 3-Dimensional model involves applying positional and normal boundary conditions determined based on one or more relationships between face portion shape and hair portion shape. In yet another embodiment, constructing the 3-Dimensional model involves using shape from shading to capture fine-scale details in a form of surface normals, the shape from shading based on an adaptive albedo model and/or a lighting condition estimated based on shape fitting the face portion.

Abstract: Techniques are provided for incrementally aligning multiple scans of a three-dimensional subject. This can be accomplished by establishing an updated aligned set of scans as each new scan is sequentially processed and aligned with the existing scans. In such embodiments the pairwise and global alignment processes are effectively combined into a single collective alignment process. This collective alignment converges to an optimal alignment faster than the sequential pairwise alignment process that existing solutions use. The collective alignment enforces pairwise alignment between the individual scans in the aligned set of scans. This is because each scan comprising the aligned set can be aligned to the next incremental scan if any scan included in the aligned set can be aligned to the next incremental scan. The pairwise alignment between the scans comprising the aligned set is thus a known function.

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

Abstract: Techniques for facial expression capture for character animation are described. In one or more implementations, facial key points are identified in a series of images. Each image, in the series of images, is normalized from the identified facial key points. Facial features are determined from each of the normalized images. Then a facial expression is classified, based on the determined facial features, for each of the normalized images. In additional implementations, a series of images are captured that include performances of one or more facial expressions. The facial expressions in each image of the series of images are classified by a facial expression classifier. Then the facial expression classifications are used by a character animator system to produce a series of animated images of an animated character that include animated facial expressions that are associated with the facial expression classification of the corresponding image in the series of images.

Abstract: Techniques for facial expression capture for character animation are described. In one or more implementations, facial key points are identified in a series of images. Each image, in the series of images, is normalized from the identified facial key points. Facial features are determined from each of the normalized images. Then a facial expression is classified, based on the determined facial features, for each of the normalized images. In additional implementations, a series of images are captured that include performances of one or more facial expressions. The facial expressions in each image of the series of images are classified by a facial expression classifier. Then the facial expression classifications are used by a character animator system to produce a series of animated images of an animated character that include animated facial expressions that are associated with the facial expression classification of the corresponding image in the series of images.

Abstract: One embodiment involves receiving a fine mesh as input, the fine mesh representing a 3-Dimensional (3D) model and comprising fine mesh polygons. The embodiment further involves identifying, based on the fine mesh, near-planar regions represented by a coarse mesh of coarse mesh polygons, at least one of the near-planar regions corresponding to a plurality of the coarse mesh polygons. The embodiment further involves determining a deformation to deform the coarse mesh based on comparing normals between adjacent coarse mesh polygons. The deformation may involve reducing a first angle between coarse mesh polygons adjacent to one another in a same near-planar region. The deformation may additionally or alternatively involve increasing an angle between coarse mesh polygons adjacent to one another in different near-planar regions. The fine mesh can be deformed using the determined deformation.

Abstract: One embodiment involves receiving a fine mesh as input, the fine mesh representing a 3-Dimensional (3D) model and comprising fine mesh polygons. The embodiment further involves identifying, based on the fine mesh, near-planar regions represented by a coarse mesh of coarse mesh polygons, at least one of the near-planar regions corresponding to a plurality of the coarse mesh polygons. The embodiment further involves determining a deformation to deform the coarse mesh based on comparing normals between adjacent coarse mesh polygons. The deformation may involve reducing a first angle between coarse mesh polygons adjacent to one another in a same near-planar region. The deformation may additionally or alternatively involve increasing an angle between coarse mesh polygons adjacent to one another in different near-planar regions. The fine mesh can be deformed using the determined deformation.

Abstract: Techniques are provided for incrementally aligning multiple scans of a three-dimensional subject. This can be accomplished by establishing an updated aligned set of scans as each new scan is sequentially processed and aligned with the existing scans. In such embodiments the pairwise and global alignment processes are effectively combined into a single collective alignment process. This collective alignment converges to an optimal alignment faster than the sequential pairwise alignment process that existing solutions use. The collective alignment enforces pairwise alignment between the individual scans in the aligned set of scans. This is because each scan comprising the aligned set can be aligned to the next incremental scan if any scan included in the aligned set can be aligned to the next incremental scan. The pairwise alignment between the scans comprising the aligned set is thus a known function.

Abstract: Systems and methods are disclosed herein for 3-Dimensional portrait reconstruction from a single photo. A face portion of a person depicted in a portrait photo is detected and a 3-Dimensional model of the person depicted in the portrait photo constructed. In one embodiment, constructing the 3-Dimensional model involves fitting hair portions of the portrait photo to one or more helices. In another embodiment, constructing the 3-Dimensional model involves applying positional and normal boundary conditions determined based on one or more relationships between face portion shape and hair portion shape. In yet another embodiment, constructing the 3-Dimensional model involves using shape from shading to capture fine-scale details in a form of surface normals, the shape from shading based on an adaptive albedo model and/or a lighting condition estimated based on shape fitting the face portion.

Abstract: Techniques for facial expression capture for character animation are described. In one or more implementations, facial key points are identified in a series of images. Each image, in the series of images, is normalized from the identified facial key points. Facial features are determined from each of the normalized images. Then a facial expression is classified, based on the determined facial features, for each of the normalized images. In additional implementations, a series of images are captured that include performances of one or more facial expressions. The facial expressions in each image of the series of images are classified by a facial expression classifier. Then the facial expression classifications are used by a character animator system to produce a series of animated images of an animated character that include animated facial expressions that are associated with the facial expression classification of the corresponding image in the series of images.

Abstract: Alignment techniques are described that automatically align multiple scans of an object obtained from different perspectives. Instead of relying solely on errors in local feature matching between a pair of scans to identify a best possible alignment, additional alignment possibilities may be considered. Grouped keypoint features of the pair of scans may be compared to keypoint features of an additional scan to determine an error between the respective keypoint features. Various alignment techniques may utilize the error to determine an optimal alignment for the scans.

Abstract: The subject disclosure is directed towards reconstructing an approximate hair surface using refinement of hair strands. Hair strands are first extracted from 2D images of a camera array, and projected onto a 3D visual hull. The 3D positions of these strands are refined by optimizing an objective function that takes into account orientation consistency, a visual hull constraint and/or smoothness constraints defined at the strand, wisp and/or global levels.

Abstract: One embodiment involves receiving a fine mesh as input, the fine mesh representing a 3-Dimensional (3D) model and comprising fine mesh polygons. The embodiment further involves identifying, based on the fine mesh, near-planar regions represented by a coarse mesh of coarse mesh polygons, at least one of the near-planar regions corresponding to a plurality of the coarse mesh polygons. The embodiment further involves determining a deformation to deform the coarse mesh based on comparing normals between adjacent coarse mesh polygons. The deformation may involve reducing a first angle between coarse mesh polygons adjacent to one another in a same near-planar region. The deformation may additionally or alternatively involve increasing an angle between coarse mesh polygons adjacent to one another in different near-planar regions. The fine mesh can be deformed using the determined deformation.

Abstract: The subject disclosure is directed towards reconstructing an approximate hair surface using refinement of hair strands. Hair strands are first extracted from 2D images of a camera array, and projected onto a 3D visual hull. The 3D positions of these strands are refined by optimizing an objective function that takes into account orientation consistency, a visual hull constraint and/or smoothness constraints defined at the strand, wisp and/or global levels.

Abstract: The disclosure provides a technique for recursively partitioning a 3D model of an object into two or more components such that each component fits within a predefined printing volume. The technique includes determining a set of planar cuts each of which partitions the 3D model into at least two components, evaluating one or more objective functions for each cut in the set of planar cuts, and selecting a cut from the set of planar cuts based on the evaluations of the objective functions. In addition, the technique includes, upon determining that a component resulting from the selected cut does not fit within the predefined printing volume, further partitioning that component.