Abstract: A computer-implemented method for decomposing videos into multiple layers (212, 213) that can be re-combined with modified relative timings includes obtaining video data including a plurality of image frames (201) depicting one or more objects. For each of the plurality of frames, the computer-implemented method includes generating one or more object maps descriptive of a respective location of at least one object of the one or more objects within the image frame. For each of the plurality of frames, the computer-implemented method includes inputting the image frame and the one or more object maps into a machine-learned layer Tenderer model. (220) For each of the plurality of frames, the computer-implemented method includes receiving, as output from the machine-learned layer Tenderer model, a background layer illustrative of a background of the video data and one or more object layers respectively associated with one of the one or more object maps.

Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.

Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

Abstract: Structural health monitoring (SHM) is essential but can be expensive to perform. In an embodiment, a method includes sensing vibrations at a plurality of locations of a structure by a plurality of time-synchronized sensors. The method further includes determining a first set of dependencies of all sensors of the time-synchronized sensors at a first sample time to any sensors of a second sample time, and determining a second set of dependencies of all sensors of the time-synchronized sensors at the second sample time to any sensors of a third sample time. The second sample time is later than the first sample time, and the third sample time is later than the second sample time. The method then determines whether the structure has changed if the first set of dependencies is different from the second set of dependencies. Therefore, automated SHM can ensure safety at a lower cost to building owners.

Abstract: A method and system of converting stereo video content to multi-view video content combines an Eulerian approach with a Lagrangian approach. The method comprises generating a disparity map for each of the left and right views of a received stereoscopic frame. For each corresponding pair of left and right scanlines of the received stereoscopic frame, the method further comprises decomposing the left and right scanlines into a left sum of wavelets or other basis functions, and a right sum wavelets or other basis functions. The method further comprises establishing an initial disparity correspondence between left wavelets and right wavelets based on the generated disparity maps, and refining the initial disparity between the left wavelet and the right wavelet using a phase difference between the corresponding wavelets. The method further comprises reconstructing at least one novel view based on the left and right wavelets.

Abstract: A method and system of converting stereo video content to multi-view video content combines an Eulerian approach with a Lagrangian approach. The method comprises generating a disparity map for each of the left and right views of a received stereoscopic frame. For each corresponding pair of left and right scanlines of the received stereoscopic frame, the method further comprises decomposing the left and right scanlines into a left sum of wavelets or other basis functions, and a right sum wavelets or other basis functions. The method further comprises establishing an initial disparity correspondence between left wavelets and right wavelets based on the generated disparity maps, and refining the initial disparity between the left wavelet and the right wavelet using a phase difference between the corresponding wavelets. The method further comprises reconstructing at least one novel view based on the left and right wavelets.

Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

Abstract: A method and system of converting stereo video content to multi-view video content combines an Eulerian approach with a Lagrangian approach. The method comprises generating a disparity map for each of the left and right views of a received stereoscopic frame. For each corresponding pair of left and right scanlines of the received stereoscopic frame, the method further comprises decomposing the left and right scanlines into a left sum of wavelets or other basis functions, and a right sum wavelets or other basis functions. The method further comprises establishing an initial disparity correspondence between left wavelets and right wavelets based on the generated disparity maps, and refining the initial disparity between the left wavelet and the right wavelet using a phase difference between the corresponding wavelets. The method further comprises reconstructing at least one novel view based on the left and right wavelets.

Abstract: An apparatus according to an embodiment of the present invention enables measurement and visualization of a refractive field such as a fluid. An embodiment device obtains video captured by a video camera with an imaging plane. Representations of apparent motions in the video are correlated to determine actual motions of the refractive field. A textured background of the scene can be modeled as stationary, with a refractive field translating between background and video camera. This approach offers multiple advantages over conventional fluid flow visualization, including an ability to use ordinary video equipment outside a laboratory without particle injection. Even natural backgrounds can be used, and fluid motion can be distinguished from refraction changes. Embodiments can render refractive flow visualizations for augmented reality, wearable devices, and video microscopes.

Abstract: A method and corresponding apparatus for measuring object motion using camera images may include measuring a global optical flow field of a scene. The scene may include target and reference objects captured in an image sequence. Motion of a camera used to capture the image sequence may be determined relative to the scene by measuring an apparent, sub-pixel motion of the reference object with respect to an imaging plane of the camera. Motion of the target object corrected for the camera motion may be calculated based on the optical flow field of the scene and on the apparent, sub-pixel motion of the reference object with respect to the imaging plane of the camera. Embodiments may enable measuring vibration of structures and objects from long distance in relatively uncontrolled settings, with or without accelerometers, with high signal-to-noise ratios.

Abstract: In one embodiment, a method comprises projecting, from a projector, a diffused on an object. The method further includes capturing, with a first camera in a particular location, a reference image of the object while the diffused is projected on the object. The method further includes capturing, with a second camera positioned in the particular location, a test image of the object while the diffused is projected on the object. The method further includes comparing speckles in the reference image to the test image. The projector, first camera and second camera are removably provided to and positioned in a site of the object.

Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

Abstract: Geometries of the structures and objects deviate from their idealized models, while not always visible to the naked eye. Embodiments of the present invention reveal and visualize such subtle geometric deviations, which can contain useful, surprising information. In an embodiment of the present invention, a method can include fitting a model of a geometry to an input image, matting a region of the input image according to the model based on a sampling function, generating a deviation function based on the matted region, extrapolating the deviation function to an image wide warping field, and generating an output image by warping the input image according to the warping. In an embodiment of the present invention, Deviation Magnification inputs takes a still image or frame, fits parametric models to objects of interest, and generates an output image exaggerating departures from ideal geometries.

Abstract: The method for dynamic video magnification magnifies small motions occurring simultaneously within large motions. The method involves selecting a region of interest from a video for magnification. The region of interest is warped to obtain a stabilized sequence of frames that discounts large motions. Each frame of the stabilized sequence is decomposed to a foreground layer, a background layer, and an alpha matte layer, and each of the foreground and alpha matte layers is magnified. Then a magnified sequence is generated from the magnified layers using matte inversion. Any image holes in the magnified sequence are filled in using texture synthesis. Finally, the magnified sequence is de-warped to the original space-time coordinates.

Abstract: In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.

Abstract: A method and corresponding apparatus for measuring object motion using camera images may include measuring a global optical flow field of a scene. The scene may include target and reference objects captured in an image sequence. Motion of a camera used to capture the image sequence may be determined relative to the scene by measuring an apparent, sub-pixel motion of the reference object with respect to an imaging plane of the camera. Motion of the target object corrected for the camera motion may be calculated based on the optical flow field of the scene and on the apparent, sub-pixel motion of the reference object with respect to the imaging plane of the camera. Embodiments may enable measuring vibration of structures and objects from long distance in relatively uncontrolled settings, with or without accelerometers, with high signal-to-noise ratios.

Abstract: A method and system of converting stereo video content to multi-view video content combines an Eulerian approach with a Lagrangian approach. The method comprises generating a disparity map for each of the left and right views of a received stereoscopic frame. For each corresponding pair of left and right scanlines of the received stereoscopic frame, the method further comprises decomposing the left and right scanlines into a left sum of wavelets or other basis functions, and a right sum wavelets or other basis functions. The method further comprises establishing an initial disparity correspondence between left wavelets and right wavelets based on the generated disparity maps, and refining the initial disparity between the left wavelet and the right wavelet using a phase difference between the corresponding wavelets. The method further comprises reconstructing at least one novel view based on the left and right wavelets.

Abstract: A method of recovering audio signals and corresponding apparatus according to an embodiment of the present invention using video or other sequence of images enables recovery of sound that causes vibrations of a surface. An embodiment method includes combining representations of local motions of a surface to produce a global motion signal of the surface. The local motions are captured in a series of images of features of the surface, and the global motion signal represents a sound within an environment in which the surface is located. Some embodiments compare representations of local motions of a surface to determine which motions are in-phase or out-of-phase with each other, enabling visualization of surface vibrational modes. Embodiments are passive, as compared to other forms of remote audio recovery that employ active sensing, such as laser microphone systems. Example applications for the embodiments include espionage and surveillance.