Abstract: Methods and systems for measuring group behavior are provided. Group behavior of different groups may be measured objectively and automatically in different environments including a dark environment. A uniform visible signal comprising images of members of a group may be obtained. Facial motion and body motions of each member may be detected and analyzed from the signal. Group behavior may be measured by aggregating facial motions and body motions of all members of the group. A facial motion such as a smile may be detected by using the Fourier Lucas-Kanade (FLK) algorithm to register and track faces of each member of a group. A flow-profile for each member of the group is generated. Group behavior may be further analyzed to determine a correlation of the group behavior and the content of the stimulus. A prediction of the general public's response to the stimulus based on the analysis of the group behavior is also provided.

Abstract: Approaches are described for formation retrieval. Embodiments receive positional data, across an interval window, including a respective agent trajectory for each agent and an object trajectory for one or more objects. The interval window is partitioned into frames and, at each frame, embodiments calculate a cost of assigning a role to each agent based on one or more exemplar formations. A formation is determined by assigning a role to each agent based on the calculated cost. Each frame of the formation is compared to a corresponding frame of a stored formation, by calculating a distance between a position of each assigned role in the frame and a position of a corresponding role in the stored formation and by comparing the object trajectory for the one or more objects with a corresponding object trajectory in the stored formation. Based on the comparisons, a list of stored formations is generated.

Abstract: Methods and systems for measuring group behavior are provided. Group behavior of different groups may be measured objectively and automatically in different environments including a dark environment. A uniform visible signal comprising images of members of a group may be obtained. Facial motion and body motions of each member may be detected and analyzed from the signal. Group behavior may be measured by aggregating facial motions and body motions of all members of the group. A facial motion such as a smile may be detected by using the Fourier Lucas-Kanade (FLK) algorithm to register and track faces of each member of a group. A flow-profile for each member of the group is generated. Group behavior may be further analyzed to determine a correlation of the group behavior and the content of the stimulus. A prediction of the general public's response to the stimulus based on the analysis of the group behavior is also provided.

Abstract: Techniques are disclosed for creating digital assets that can be used to personalize themed products. For example, a workflow and pipeline used to generate a 3D model from digital images of a person's face and to manufacture a personalized, physical figurine customized with the 3D model are disclosed. The 3D model of the person's face may be simplified to match a topology of a desired figurine. While the topology is deformed to match that of the figurine, the 3D model retains the geometry of the child's face. Simplifying the topology of the 3D model in this manner allows the mesh to be integrated with or attached to a mesh representing desired figurine.

Abstract: Methods and systems for estimating HDR sky light probes for outdoor images are disclosed. A precaptured sky light probe database is leveraged. The database includes a plurality of HDR sky light probes captured under a plurality of different illumination conditions. A HDR sky light probe is estimated from an outdoor image by fitting a three dimensional model to an object of interest in the image and solving an inverse optimization lighting problem for the 3D model where the space of possible HDR sky light probes is constrained by the HDR sky light probes of the database.

Abstract: Approaches are described for assigning roles to agents in a group of agents engaging in an activity. An assignment analysis system receives a first set of detections, where each detection in the first set of detections comprises a physical location. The assignment analysis system defines an exemplar formation comprising an arrangement of each role in a set of roles. The assignment analysis system calculates a first cost function between at least one detection in the first set of detections and at least one role in the set of roles. The assignment analysis system generates a first set of permutations based on the first cost function. The assignment analysis system assigns a first role in the set of roles to a first detection in the first set of detections based on the first set of permutations.

Abstract: A method is disclosed for reducing distortions introduced by deformation of a surface with an existing parameterization. In one embodiment, the distortions are reduced over a user-specified convex region in texture space ensuring optimization is locally contained in areas of interest. A distortion minimization algorithm is presented that is guided by a user-supplied rigidity map of the specified region. In one embodiment, non-linear optimization is used to calculate the axis-aligned deformation of a non-uniform grid specified over the region's parameter space, so that when the space is remapped from the original to the deformed grid, the distortion of the rigid features is minimized. Since grids require minimal storage and the remapping from one grid to another entails minimal cost, grids can be precalculated for animation sequences and used for real-time texture space remapping that minimizes distortions on specified rigid features.

Abstract: Approaches are described for discovering a formation associated with an agent group engaging in an activity over a window of time. A formation analysis system computes first and second results for an objective function based on first and second sets of role assignments for each agent in the agent group at first and second moments in time, respectively. The formation analysis system iterates by: replacing the first set of role assignments with the second set of role assignments, and determining whether completion criteria have been met based at least in part on comparing the first result with the second result. If the completion criteria have not been met, then the formation analysis system replaces the second set of role assignments with a third set of role assignments that associate each agent in the first agent group with a different role assignment in the third set of role assignments at a third moment in time.

Abstract: Algorithms for improving the performance of conventional tone mapping operators (TMO) by calculating both a contrast waste score and a contrast loss score for a first tone-mapped image produced by the TMO. The two contrast scores can be used to optimize the performance of the TMO by reducing noise and improving contrast. Algorithms for generating an HDR image by converting non-linear color space images into linear color space format, aligning the images to a reference, de-ghosting the aligned images if necessary, and merging the aligned (and potentially de-ghosted) images to create an HDR image. The merging can be performed with exposure fusion, HDR reconstruction, or other suitable techniques.

Abstract: Techniques are disclosed for retargeting facial expressions. Input is received that represents a facial expression of a first character. Facial layers are generated based on the received input. The facial layers include one or more parameters extracted from the received input. A facial expression for a second character and corresponding to the facial expression of the first character is generated, based on the facial layers and without defining any spatial correspondence between the first character and the second character.

Abstract: Techniques are disclosed for creating digital assets that can be used to personalize themed products. For example, a workflow and pipeline used to generate a 3D model from digital images of a person's face and to manufacture a personalized, physical figurine customized with the 3D model are disclosed. The 3D model of the person's face may be simplified to match a topology of a desired figurine. While the topology is deformed to match that of the figurine, the 3D model retains the geometry of the child's face. Simplifying the topology of the 3D model in this manner allows the mesh to be integrated with or attached to a mesh representing desired figurine.

Abstract: To generate a media presentation of a live event, a user interface is coupled to at least three cameras that share substantially the same vantage point. One of the cameras (e.g., a context camera) provides a context view of the event that is displayed on a screen of the user interface. The views of the other two cameras are superimposed onto the context view to define sub-portions that are visually demarcated within the context view. In one embodiment, only one of views is visually demarcated in the context view at any given time. Based on user interaction, the user interface can switch between the cameras views and control the cameras to capture different portions of the context view. Based the image data captured by the views of the cameras within the context view, the user interface generates a media presentation that may be broadcast to multiple viewers.

Abstract: Techniques are disclosed for controlling robot pixels to display a visual representation of an input. The input to the system could be an image of a face, and the robot pixels deploy in a physical arrangement to display a visual representation of the face, and would change their physical arrangement over time to represent changing facial expressions. The robot pixels function as a display device for a given allocation of robot pixels. Techniques are also disclosed for distributed collision avoidance among multiple non-holonomic robots to guarantee smooth and collision-free motions. The collision avoidance technique works for multiple robots by decoupling path planning and coordination.

Abstract: Methods and systems for predicting light probes for outdoor images are disclosed. A light probe database is created to learn a mapping from the outdoor image's features to predicted outdoor light probe illumination parameters. The database includes a plurality of images, image features for each of the plurality of images, and a captured light probe for each of the plurality of images. A light probe illumination model based on a sun model and sky model is fitted to the captured light probes. The light probe for the outdoor image may be predicted based on the database dataset and fitted light probe models.

Abstract: Techniques are disclosed for generating a bilinear spatiotemporal basis model. A method includes the steps of predefining a trajectory basis for the bilinear spatiotemporal basis model, receiving three-dimensional spatiotemporal data for a training sequence, estimating a shape basis for the bilinear spatiotemporal basis model using the three-dimensional spatiotemporal data, and computing coefficients for the bilinear spatiotemporal basis model using the trajectory basis and the shape basis.

Abstract: Approaches are described for assigning roles to agents in a group of agents engaging in an activity. An assignment analysis system receives a first set of detections, where each detection in the first set of detections comprises a physical location. The assignment analysis system defines an exemplar formation comprising an arrangement of each role in a set of roles. The assignment analysis system calculates a first cost function between at least one detection in the first set of detections and at least one role in the set of roles. The assignment analysis system generates a first set of permutations based on the first cost function. The assignment analysis system assigns a first role in the set of roles to a first detection in the first set of detections based on the first set of permutations.

Abstract: Algorithms for improving the performance of conventional tone mapping operators (TMO) by calculating both a contrast waste score and a contrast loss score for a first tone-mapped image produced by the TMO. The two contrast scores can be used to optimize the performance of the TMO by reducing noise and improving contrast. Algorithms for generating an HDR image by converting non-linear color space images into linear color space format, aligning the images to a reference, de-ghosting the aligned images if necessary, and merging the aligned (and potentially de-ghosted) images to create an HDR image. The merging can be performed with exposure fusion, HDR reconstruction, or other suitable techniques.

Abstract: An improved modeling system and associated techniques are described herein. In various embodiments, a modeling system generates a spatially local PCA model where the parts are connected with continuity constraints (e.g., soft constraints) in the boundaries. Experimental results on 3D face modeling show that the spatially local PCA model generalizes better than a holistic model. Moreover, the modeling system smoothly varies local control points for face posing in animation.

Abstract: Techniques are disclosed for controlling robot pixels to display a visual representation of an input. The input to the system could be an image of a face, and the robot pixels deploy in a physical arrangement to display a visual representation of the face, and would change their physical arrangement over time to represent changing facial expressions. The robot pixels function as a display device for a given allocation of robot pixels. Techniques are also disclosed for distributed collision avoidance among multiple non-holonomic robots to guarantee smooth and collision-free motions. The collision avoidance technique works for multiple robots by decoupling path planning and coordination.

Abstract: A method is disclosed for reducing distortions introduced by deformation of a surface with an existing parameterization. In one embodiment, the distortions are reduced over a user-specified convex region in texture space ensuring optimization is locally contained in areas of interest. A distortion minimization algorithm is presented that is guided by a user-supplied rigidity map of the specified region. In one embodiment, non-linear optimization is used to calculate the axis-aligned deformation of a non-uniform grid specified over the region's parameter space, so that when the space is remapped from the original to the deformed grid, the distortion of the rigid features is minimized. Since grids require minimal storage and the remapping from one grid to another entails minimal cost, grids can be precalculated for animation sequences and used for real-time texture space remapping that minimizes distortions on specified rigid features.