Abstract: Systems and methods for articulated pose estimation are provided. Some embodiments include training a convolutional neural network for object pose estimation, which includes receiving a two-dimensional training image of an articulated object that has a plurality of components and identifying, from the two-dimensional training image, at least one key point for each of the plurality of components. Some embodiments also include testing the accuracy of the object pose estimation, which includes visualizing a three or more dimensional pose of each of the plurality of components of the articulated object from a two-dimensional testing image and providing data related to the visualization for output.

Abstract: A system and method generates a broadcast image. The method includes receiving a first image captured by a first camera having a first configuration incorporating a first center of projection. The method includes determining a first mapping from a first image plane of the first camera onto a sphere. The method includes determining a second mapping from the sphere to a second image plane of a second virtual camera having a second configuration incorporating the first center of projection of the first configuration. The method includes generating a second image based upon the first image and a concatenation of the first and second mappings.

Abstract: Systems and methods for estimating the pose of a textureless object are disclosed. A method to estimate a pose of a textureless object includes obtaining, by a processing device, a single image of the textureless object. The pose of the textureless object can be inferred from the single image. The method further includes generating, by the processing device, a three dimensional model of the textureless object from a plurality of viewpoints and a plurality of scales obtained from image data of the textureless object, matching, by the processing device, the single image with a discretized render of the three dimensional model via a multi-level illumination invariant tree structure to obtain an alignment of the single image with the discretized render, and estimating, by the processing device, the pose of the textureless object based on the alignment.

Abstract: Embodiments disclosed herein relate to a method and apparatus for generating a three-dimensional surface. In one embodiment, there is a method for generating a three-dimensional surface. The method includes capturing a plurality of images of a target object with at least two cameras, the target object illuminated by at least two sets of red-green-blue (RGB) lights positioned in an array about the target object and generating a three-dimensional surface of the target object by iteratively reconstructing a surface estimate of the target object and aligning images of the target object using motion estimation until the images converge, wherein the images are processed in n-frame intervals.

Abstract: Systems and methods for estimating the pose of a textureless object are disclosed. A method to estimate a pose of a textureless object includes obtaining, by a processing device, a single image of the textureless object. The pose of the textureless object can be inferred from the single image. The method further includes generating, by the processing device, a three dimensional model of the textureless object from a plurality of viewpoints and a plurality of scales obtained from image data of the textureless object, matching, by the processing device, the single image with a discretized render of the three dimensional model via a multi-level illumination invariant tree structure to obtain an alignment of the single image with the discretized render, and estimating, by the processing device, the pose of the textureless object based on the alignment.

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. 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: Embodiments disclosed herein relate to a method and apparatus for generating a three-dimensional surface. In one embodiment, there is a method for generating a three-dimensional surface. The method includes capturing a plurality of images of a target object with at least two cameras, the target object illuminated by at least two sets of red-green-blue (RGB) lights positioned in an array about the target object and generating a three-dimensional surface of the target object by iteratively reconstructing a surface estimate of the target object and aligning images of the target object using motion estimation until the images converge, wherein the images are processed in n-frame intervals.

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: 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: 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 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: Techniques are disclosed for augmenting hand-drawn animation of human characters with three-dimensional (3D) physical effects to create secondary motion. Secondary motion, or the motion of objects in response to that of the primary character, is widely used to amplify the audience's response to the character's motion and to provide a connection to the environment. These 3D effects are largely passive and tend to be time consuming to animate by hand, yet most are very effectively simulated in current animation software. The techniques enable hand-drawn characters to interact with simulated objects such as cloth and clothing, balls and particles, and fluids. The driving points or volumes for the secondary motion are tracked in two dimensions, reconstructed into three dimensions, and used to drive and collide with the simulated objects.

Abstract: A system and method generates a broadcast image. The method includes receiving a first image captured by a first camera having a first configuration incorporating a first center of projection. The method includes determining a first mapping from a first image plane of the first camera onto a sphere. The method includes determining a second mapping from the sphere to a second image plane of a second virtual camera having a second configuration incorporating the first center of projection of the first configuration. The method includes generating a second image based upon the first image and a concatenation of the first and second mappings.

Abstract: Body-mounted cameras are used to accurately reconstruct the motion of a subject. Outward-looking cameras are attached to the limbs of the subject, and the joint angles and root pose that define the subject's configuration are estimated through a non-linear optimization, which can incorporate image matching error and temporal continuity of motion. Instrumentation of the environment is not required, allowing for motion capture over extended areas and in outdoor settings.

Abstract: A relative pose between two cameras is determined by using input data obtained from the motion of subjects, such as pedestrians, between the fields of view of two cameras, determining trajectory information for the subjects, and computing homographies relating lines obtained from trajectories in the first image data to lines obtained from the trajectories in the second image data. The two fields of view need not overlap.

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: A relative pose between two cameras is determined by using input data obtained from the motion of subjects, such as pedestrians, between the fields of view of two cameras, determining trajectory information for the subjects, and computing homographies relating lines obtained from trajectories in the first image data to lines obtained from the trajectories in the second image data. The two fields of view need not overlap.

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: A relative pose between two cameras is determined by using input data obtained from the motion of subjects, such as pedestrians, between the fields of view of two cameras, determining trajectory information for the subjects, and computing homographies relating lines obtained from trajectories in the first image data to lines obtained from the trajectories in the second image data. The two fields of view need not overlap.