Abstract: Embodiments are generally directed to minimum or maximum sample indexing in a control surface. An embodiment of an apparatus includes a graphics processor including: a sampler to sample a value; one or more of a color unit or a depth unit; and at least one minimum or maximum sample (min/max) setter subunit for the color unit or depth unit, the min/max setter subunit to receive a new sample value, store the sample value in a resource containing a plurality of sample values, and update indexing include index values for one or more of a minimum sample value and a maximum sample value in the plurality of sample values of the resource.

Abstract: A method includes: presenting, on a device, a view of at least part of an augmented reality (AR) environment, the AR environment including a first AR location corresponding to a first physical location in a physical environment; initiating a download to the device of first data representing a first AR object associated with the first AR location; assigning a size parameter to a first loading indicator for the first AR object based on a size of the first AR object; determining a spatial relationship between the view and the first physical location; and presenting the first loading indicator in the view, the first loading indicator having a size based on the assigned size parameter and being presented at a second AR location based on the determined spatial relationship.

Abstract: Systems, methods, and computer-readable media are disclosed for generating or modifying a holographic object based on user commands. Holographic projectors, which may be integrated with a user device, may be controlled to project a holographic grid that can be manipulated by a user to provide design commands to the user device. The user device may be configured to interpret the design commands and generate a holographic object based thereon. The holographic grid may include a plurality of cuboid cells. A user may, through gesture-based commands, indicate, for any given cell in the holographic grid, whether or not a portion of the holographic object should be generated in a three-dimensional spatial position corresponding to the cell. In addition, a user can provide gesture-based commands to selected cells of the holographic grid corresponding to portions of an existing holographic object that the user wishes to remove.

Abstract: A tiling unit assigning primitives to tiles in a graphics processing system which has a rendering space subdivided into a plurality of tiles. Each tile can comprise one or more polygonal region. Mesh logic of the tiling unit can determine that a plurality of primitives form a mesh and can determine whether the mesh entirely covers a region. If the mesh entirely covers the region then a depth threshold for the region can be updated so that subsequent primitives which lie behind the depth threshold are culled (i.e. not included in the display list for a tile). This helps to reduce the number of primitive IDs included in a display list for a tile which reduces the amount of memory used by the display list and reduces the number of primitives which a hidden surface removal (HSR) module needs to fetch to perform HSR on the tile.

Abstract: Embodiments relate to enabling a user of data-sharing applications executing on a computing device to indirectly exchange objects between the applications by adding objects from the applications to a journal application that manages a display area. The objects are displayed in the display area. The journal application collects metadata related to the objects and automatically curates lists of the objects according to the metadata. Curation of a list may involve moving objects into a list, merging objects, creating new objects out of content of existing objects, grouping objects according to a commonality thereof, etc. Machine learning services may be invoked to acquire additional metadata about the objects and to make curation decisions.

Abstract: A method for learning a pedestrian detector to be used for robust surveillance or military purposes based on image analysis is provided for a solution to a lack of labeled images and for a reduction of annotation costs. The method can be also performed by using generative adversarial networks (GANs). The method includes steps of: a learning device generating an image patch by cropping each of regions on a training image, and instructing an adversarial style transformer to generate a transformed image patch by converting each of pedestrians into transformed pedestrians capable of impeding a detection; and generating a transformed training image by replacing each of the regions with the transformed image patch, instructing the pedestrian detector to detecting the transformed pedestrians, and learning parameters of the pedestrian detector to minimize losses. This learning, as a self-evolving system, is robust to adversarial patterns by generating training data including hard examples.

Abstract: Disclosed is a parametric feature-based 3D CAD system that allows multiple users to simultaneously edit a parametric feature-based 3D CAD model consisting of 3D parts and assemblies of those parts (3D Model). Several CAD users, each using their own computer, phone, or tablet, can edit the same 3D Model at the same time. Editing may be separate and simultaneous—there is no need for users to worry about locking, checking out, or otherwise restricting each other's access to 3D Models. As a result, users see each other's changes occur in real-time, and may also identify what aspects other users are actively modifying through visible Collaboration Cues.

Abstract: Provided is a system and method for generating an optimized 3D model. The system includes a processor for receiving a high-poly 3D model, wherein the processor is configured to: divide the high-poly 3D model into a plurality of subcomponents, approximate each subcomponent of the plurality of subcomponents by a geometric shape, adjust the geometric shape to conform to the subcomponent to the geometric shape, merge the adjusted geometric shapes to form a reduced 3D model, and texture map the reduced 3D model to provide texture of the high-poly 3D model to form the optimized 3D model. The system also includes a memory connected to the processor for storing the high-poly 3D model and the optimized 3D model and a 3D model display for displaying the optimized 3D model.

Abstract: Roughly described, a method for determining characteristics of a body by simulation, useful in analyzing semiconductor devices, includes imposing a Delaunay mesh on a simulated body to be modeled, determining a system of node equations describing generation and flux of a set of at least a first physical quantity at each node in the mesh, and numerically solving the system of node equations to identify the physical quantities in the set at each node in the mesh, where the flux of the first physical quantity in the body, as represented in the node equations, is anisotropic. The method does not impose any limitation on the geometry of the device, on mesh elements, or on the orientation of the anisotropy.

Abstract: A method includes receiving head-tracking data that describes one or more positions of one or more people while the one or more people are viewing a three-dimensional video. The method further includes generating video segments from the three-dimensional video. The method further includes, for each of the video segments: determining a directional encoding format that projects latitudes and longitudes of locations of a surface of a sphere onto locations on a plane, determining a cost function that identifies a region of interest on the plane based on the head-tracking data, and generating optimal segment parameters that minimize a sum-over position for the region of interest.

Abstract: Unstructured grids are automatically constructed in a domain containing complex internal boundaries. Simulation grids are constructed for reservoirs or fields which contain complex fault planes. Reconciling among generated fault grid-points and other reservoir/field grid-points is performed, enabling the use of unconstrained Delaunay triangulation. High-quality orthogonal unstructured grids are provided with good convergence properties for reservoir simulation.

Abstract: The present approach relates to the use of a point cloud of an object to initialize or seed a space carving technique used to generate a 3D model of the object. In one implementation, feature matching is performed on 2D images, with matched features constituting the points of a point cloud model. The point cloud generated in this manner, is one input of a foreground/background segmentation algorithm, which generates a set of segmented 2D images used by a space carving routine to generate a 3D model of the object.

Abstract: A method, apparatus and computer readable medium for performing a computer simulation to predict the behavior or response of a physical object includes receiving at least one selection made by a user with respect to a context of the computer simulation to be performed. Based on the at least one selection, a list of tools, objects and properties is filtered to be displayed to the user with respect to the computer simulation to be performed, to display only those tools, object and properties that are pertinent to the context of the computer simulation to be performed. The filtered listed of tools, objects and properties with respect to the computer simulation is displayed, to obtain user input of which of the tools, objects and properties are to be utilized in the computer simulation.

Abstract: In one example of the disclosure, presence data indicative of a presence factor for a remote subject is received from a server. The presence data is analyzed and a display representative of the presence factor is caused at a 3D object. The 3D object includes a 3D element representative of the remote subject.

Abstract: A display apparatus includes: a display unit configured to display an image on a screen; an input unit configured to receive an input from a user; and a control unit configured to control the display unit to display a thumbnail image corresponding to a partial region of a preview image of an omnidirectionally captured image. The control unit is further configured to control the display unit to display an image corresponding to a specific region of the preview image if the input is received. At least one of the specific region and an enlargement ratio of the image corresponding to the specific region is determined based on the input.

Abstract: A system and method for identifying a break in a broadcast including receiving a broadcast of an event, the broadcast comprising one of audio and video, receiving event data about the event, determining, during the event, a break threshold based on the event data and a type of the event and identifying a break based on the broadcast of the event and the break threshold.

Abstract: A computing system, including at least one imaging sensor configured to collect imaging data of a physical environment. The computing system may further include a processor configured to generate, based on the imaging data, a first anchor graph including a first plurality of anchors connected by a first plurality of edges. Each anchor of the first plurality of anchors may indicate a respective estimated position in the physical environment. The processor may be further configured to detect a change in the estimated position of at least one anchor of the first plurality of anchors relative to the at least one imaging sensor. Based on the change in the estimated position, the processor may reposition the first anchor graph relative to the at least one imaging sensor. Estimated lengths of the first plurality of edges and estimated angles between the first plurality of edges may remain fixed.

Abstract: A computer system and method for performing 3D geolocation within an urban environment to at least a building floor level by combining geocoded locations with local dimensional data available from municipal agencies processed to calculate estimated elevation of building floors in a target building. The local dimensional data is building inventory information that includes the ground elevation of the target building, the number of above-ground floors in the target building and the height of the target building. The system is configured to calculate the building floor level of a particular floor in the target building from the local data. Standard equations for estimating the height of a building are adapted to generate the elevation of the particular floor within the target building relative to the ground elevation of the target building.

Abstract: Optimizations are provided for reconstructing geometric surfaces for an environment that includes moving objects. Multiple depth maps for the environment are created, where some of the depth maps correspond to different perspectives of the environment. A motion state identifier is assigned to at least some pixels in at least some of the depth maps corresponding to moving objects in the environment. A composite 3D mesh is built using at least some of the multiple depth maps, by incorporating pixel information from the depth maps, while omitting pixel information identified by the motion state identifiers as being associated with moving objects.

Abstract: Sensor fusion is utilized in an electronic device such as a head mounted display (HMD) device that has a sensor package equipped with different sensors so that information that is supplemental to captured 2D images of objects or scenes in a real world environment may be utilized to determine an optimized transform of image stereo-pairs and to discard erroneous data that would otherwise prevent successful scans used for construction of a 3D model in, for example, virtual world applications. Such supplemental information can include one or more of world location, world rotation, image data from an extended field of view (FOV), or depth map data.

Abstract: A controller for use in an additive manufacturing system including a consolidation device configured to consolidate material is provided. The controller is configured to receive a build file for a component including a plurality of build layers, wherein each build layer includes a component outer perimeter, at least one build layer generating function, at least one generating function variable, and at least one generating function constant. The controller is configured to generate at least one control signal to control a power output throughout at least one scan path of the consolidation device across the material for each build layer of the plurality of build layers, the at least one scan path generated based at least partially on the component outer perimeter, the at least one generating function, the at least one generating function variable, and the at least one generating function constant for each build layer.

Abstract: In a method and system for scanning a structure, a structure scanner may acquire multiple scans of a surface of a structure. Each of the scans may correspond to different portions of the surface. The property inspection system may generate a 3D model of the surface using the scans. To account for potential changes in position and/or orientation of the structure scanner between scans, the structure scanner may self-calibrate using a fiducial marker. By correcting for changes in position and orientation over time, the structure scanner may accurately map the scans of the different portions of the surface to a 3D model of the surface.

Abstract: A system of calibrating a multi-camera device that include two or more planar calibration targets, arranged in a non-planar orientation. The system mechanically moves the calibration targets relative to the multi-camera device to change the relative orientation. The system records images with the multi-camera device at various orientations. The recorded images contain one or more of the constituent planar calibration targets. The system identifies and extracts the pixel coordinates of each constituent planar calibration target from each image.

Abstract: A stereoscopic vision system uses at least two cameras having different parameters to image a scene and create stereoscopic views. The different parameters of the two cameras can be intrinsic or extrinsic, including, for example, the distortion profile of the lens in the cameras, the field of view of the lens, the orientation of the cameras, the positions of the cameras, the color spectrum of the cameras, the frame rate of the cameras, the exposure time of the cameras, the gain of the cameras, the aperture size of the lenses, or the like. An image processing apparatus is then used to process the images from the at least two different cameras to provide optimal stereoscopic vision to a display.

Abstract: An image processing apparatus includes an image acquisition part that acquires a plurality of different measured images, a modeling part that identifies, for each pixel, a modeled parameter approximating an approximation function of a data sequence where pixel values of pixels corresponding to the respective measured images are placed in an order of capturing, a reconstructed image generation part that generates reconstructed images which are images corresponding to the respective measured images and reconstructed with an approximation value of each pixel identified based on the modeled parameter of each pixel, and an image changing part that changes the pixel values of the measured images based on statistics of the pixel values of the measured images and that of the corresponding reconstructed images.

Abstract: Cells of an n-dimensional object are indexed. A plurality of indexing digits are grouped for each axis of the n dimensions of the n-dimensional object. A first indexing digit of a given group is allocated to each of at least two cells resulting from at least one subdivision of the dimension of the object along the axis of the given group; and an mth subsequent indexing digit of the given group is allocated to any subsequent at least two cells resulting from any subsequent at least one subdivision of at least one cell of the at least two cells resulting from the m?1th subdivision of the dimension of the object along the axis of the given group.

Abstract: A method, system and computer program product for classifying an image or video. An image or video to be classified is received. Scene statistics (statistical model of pictures, images or videos representative of pictures, images or videos, respectively, that are captured of the physical world) of the image or video are captured. A model (a statistical model that describes a set of probability distributions) of the image or video is then created using the captured scene statistics. A comparison between the model of the image or video with two other models of images or videos is performed, such as a model of visible light images or videos and a model of infrared images or videos. The received image or video is then classified (e.g., classified as corresponding to a visible light image) based on the comparison.

Abstract: An image processing apparatus generating geometric data of an object includes an obtaining unit configured to obtain a plurality of images of the object, each image captured from different viewpoints, a generating unit configured to generate geometric data of the object from the images obtained by the obtaining unit, and a correcting unit configured to correct the geometric data based on a reliability of at least a part of the geometric data generated by the generating unit.

Abstract: A system, computer-readable medium, and method for localization and mapping for an autonomous vehicle are provided. The system may obtain an image. The system may assign labels to one or more objects of the image. The system may also obtain a point cloud. The system may determine one or more object clusters of the point cloud and associate the labels assigned to the one or more objects of the image with points of the object clusters of the point cloud. The system may further identify three-dimensional (3D) objects of the point cloud based on the labels associated with the points of the object clusters. In some aspects, the system may remove dynamic traffic participants from the point cloud based on the identified 3D objects and/or perform a simultaneous localization and mapping operation on the point cloud after removing the dynamic traffic participants.

Abstract: The disclosure pertains to techniques for operation of graphics systems and task execution on a graphics processor.

Abstract: Generation of an inappropriate image portion in an orthographic image due to occlusion is prevented. An image processing device includes an image data receiving part that receives image data of multiple photographed images taken by photographing an object from different positions, a coordinate designating part that receives designation of a specific position in the object, and an optimum-condition satisfying image selecting part that selects a photographed image that is taken from a direction in a specific range relative to the specific position, from among the multiple photographed images. The selected photographed image is used to obtain pixel information of the specific position.

Abstract: Systems and methods for detecting grasping poses for handling target objects is disclosed. The system solves problem of grasp pose detection and finding suitable graspable affordance for picking objects from a confined and cluttered space, such as the bins of a rack in a retail warehouse by creating multiple surface segments within bounding box obtained from a neural network based object recognition module. Surface patches are created using a region growing technique in depth space based on surface normals directions. A Gaussian Mixture Model based on color and depth curvature is used to segment surfaces belonging to target object from background, thereby overcoming inaccuracy of object recognition module trained on a smaller dataset resulting in larger bounding boxes for target objects. Target object shape is identified by using empirical rules on surface attributes thereby detecting graspable affordances and poses thus avoiding collision with neighboring objects and grasping objects more successfully.

Abstract: A computer-implemented method for recognizing a plurality of real-world toy construction elements of a toy construction system assembled to form a real-world toy construction model, each real-world toy construction element comprising coupling members for detachably connecting the real-world toy construction element with one or more other real-world toy construction elements of the toy construction system so as to form the real-world toy construction model; wherein the method comprises: receiving at least one captured image of the real world toy construction model; processing the at least one captured image so as to at least preliminarily recognise at least a first real-world toy construction element in the at least one captured image as a first known real-world toy construction element from stored digital representations of a plurality of known real-world toy construction elements of the toy construction system, each digital representation comprising connectivity information indicative of how the correspondin

Abstract: A game system comprising a data processing system and an identification toy element that includes information associated with the identification toy element; wherein the identification toy element is a toy construction element comprising one or more connectors configured for mechanically connecting one or more other toy construction elements to the identification toy element so as to allow a user to construct a toy construction model; and wherein the data processing system is configured to: detect a presence of the identification toy element in a detection area; create an association between a virtual object in a virtual environment and the detected identification toy element; access, when the identification toy element is again placed within a detection area, the information associated with the identification toy element; obtain, based on the accessed information, information about the virtual object associated with the identification toy element; present a representation of the associated virtual object; an

Abstract: The present disclosure provides a method and apparatus for reconstructing 3D information of an object. The method of reconstructing 3D information of an object may include: reconstructing 3D information of a background space, using at least one of images of the background space for three-dimensionally reconstructing the object; separating the object from the background space on the basis of at least one of images of the object in the background space, and of obtaining a depth image of the object separated from the background space; and generating 3D information of the object based on images taken by at least one of cameras in consideration of position relationships between the depth image of the object and the cameras.

Abstract: A waveguide apparatus includes a planar waveguide and at least one optical diffraction element (DOE) that provides a plurality of optical paths between an exterior and interior of the planar waveguide. A phase profile of the DOE may combine a linear diffraction grating with a circular lens, to shape a wave front and produce beams with desired focus. Waveguide apparati may be assembled to create multiple focal planes. The DOE may have a low diffraction efficiency, and planar waveguides may be transparent when viewed normally, allowing passage of light from an ambient environment (e.g., real world) useful in AR systems. Light may be returned for temporally sequentially passes through the planar waveguide. The DOE(s) may be fixed or may have dynamically adjustable characteristics. An optical coupler system may couple images to the waveguide apparatus from a projector, for instance a biaxially scanning cantilevered optical fiber tip.

Abstract: A method and system for graphical enumeration. The method includes creating an ordered set of vertices for a graph such that each vertex is associated with a corresponding index, and wherein each vertex in the ordered set of vertices includes information. A plurality of keys is created for defining the information. A plurality of lists of vertices is created, each of which is associated with a corresponding key such that vertices in a corresponding list include information associated with the corresponding key. For a first list of vertices, a least valued index is determined from a group of associated vertices based on vertices in the first list and vertices pointed to by the vertices in the first list. Also, all associated vertices are pointed to a root vertex associated with the least valued index.

Abstract: A two-dimensional drawing of a three-dimensional wire harness model is generated by selecting a starting node from a plurality of nodes of the three-dimensional wire harness model, where the starting node is directly connected to a first bundle and a second bundle of the plurality of bundles, wherein further each of the first and second bundles are representable by corresponding first and second vectors. A reference plane is defined based on an orientation of the starting node, the first vector and the second vector, such that a first adjacent node may then be mapped onto the reference plane by geometric translation. Thereafter, a plurality of mapping operations are sequentially carried out until each of the plurality of nodes and the plurality of bundles have been mapped, by geometric translation, to the reference plane, and wherein corresponding translation matrices are stored in association with corresponding ones of the plurality of mapped nodes and/or the plurality of mapped bundles.

Abstract: Distances between geographic real-world entities modeled as geometric shapes are measured. At least two shapes are positioned in a coordinate space based on their respective sets of points. A non-empty quadrant set from a plurality of non-empty quadrant sets formed of non-empty quadrants in the coordinate space is identified such that the non-empty quadrants of the identified quadrant set associated with each of the at least two shapes satisfy a predetermined condition and a distance between portions of the at least two shapes in the non-empty quadrants of the identified non-empty quadrant set is an optimal value for the requested distance. The distance between the portions of the shapes in the identified quadrant set is determined to be the requested distance.

Abstract: One embodiment of the present invention provides a system for using a mobile device to remotely control a desktop application that was configured for use with a pointing device. During operation, the system receives at a mobile device, from a user, a connection request to connect to a desktop application executing on a remote device. In response to the connection request, the system establishes a remote control session between the mobile device and the remote device. Next, the system receives, at the mobile device, a video stream from a first camera coupled to the mobile device. The system then analyzes the video stream, at the mobile device, to identify a gesture made by the user. Next, the system identifies, at the mobile device, a pointing device command corresponding to the gesture. Finally, the system sends the pointing device command to the desktop application executing on the remote device.

Abstract: One embodiment of the present invention provides a system for using a mobile device to remotely control a desktop application that was configured for use with a pointing device. During operation, the system receives at a mobile device, from a user, a connection request to connect to a desktop application executing on a remote device. In response to the connection request, the system establishes a remote control session between the mobile device and the remote device. Next, the system receives, at the mobile device, a video stream from a first camera coupled to the mobile device. The system then analyzes the video stream, at the mobile device, to identify a gesture made by the user. Next, the system identifies, at the mobile device, a pointing device command corresponding to the gesture. Finally, the system sends the pointing device command to the desktop application executing on the remote device.

Abstract: An image processing apparatus includes a first processor configured to obtain, from a color image, an illumination element image and an albedo element image corresponding to the color image, and a second processor configured to divide the illumination element image into a plurality of subelement images each corresponding to the color image.

Abstract: Provided are a method and a corresponding apparatus for modeling a deformable body including particles that define a strain energy generated by an external force with respect to a deformable body including particles, and control a displacement of the deformable body based on a volume of the particles corresponding to the displacement of the deformable body, where the displacement is determined based on the strain energy.

Abstract: A method and system for determining the location of objects using a plurality of full motion video cameras where the location is based on the intersecting portions of a plurality of three-dimensional shapes that are generated from the video data provided by the cameras. The three-dimensional shapes include two-dimensional shapes that contain predetermined traits in each of the frames of the video signals.

Abstract: A method for analyzing performance of an imaging device including a scanner with a phantom includes receiving image data related to a scanning, by the scanner, of a first part of the phantom including at least part of a first test component. The method also includes obtaining at least one positioning parameter indicative of a positioning manner of the phantom during the scanning. The method further includes generating a first test image based on the received image data and determining a first region of interest (ROI) related to the first test component in the first test image based on the at least one positioning parameter.

Abstract: A target view to a 3D scene depicted by a multiview image is determined. The multiview image comprising sampled views at sampled view positions distributed throughout a viewing volume. Each sampled view in the sampled views comprises a wide-field-of-view (WFOV) image and a WFOV depth map as seen from a respective sampled view position in the sampled view positions. The target view is used to select, from the sampled views, a set of sampled views. A display image is caused to be rendered on a display of a wearable device. The display image is generated based on a WFOV image and a WFOV depth map for each sampled view in the set of sampled views.

Abstract: Partial-image search criteria are derived that include a combination of multiple partial-image user selections of portions of at least one image. Visual search results are returned responsive to a search for images that correspond to the derived partial-image search criteria. The visual search results include at least one identified image that includes features that correspond to the derived partial-image search criteria that include the combination of the multiple partial-image user selections.

Abstract: Data processing systems are disclosed for determining semantic and person keypoints for an environment and an image and matching the keypoints for the image to the keypoints for the environment. A homography is generated based on the keypoint matching and decomposed into a matrix. Camera parameters are then determined from the matrix. A plurality of random camera poses can be generated and used to project keypoints for an environment using image keypoints. The projected keypoints can be compared to the actual keypoints for the environment to determine an error and weighting for each of the random camera poses.

Abstract: Systems, methods, devices, and non-transitory media of various embodiments render vector data on static and dynamic surfaces by a computing device for a graphic display or for a separate computing device and/or algorithm to generate an image. Complex vector data associated with a surface for rendering may be rendered. The complex vector data may be decomposed into one or more vector subunits. A geometry corresponding to a volume and a mathematical description of an extrusion of each corresponding vector subunit may be generated. The volume and the mathematical description of the extrusion may intersect a surface level-of-detail of the surface. The geometry may be rasterized as a screen-space decal. Also, a surface depth texture may be compared for the surface against the extrusion using at least the screen-space decal. In addition, geometry batching may be performed for drawing simultaneously a plurality of the one or more vector subunits.

Abstract: A method, system and medium for improving the quality of 2D-to-3D automatic conversion in a computing device by using machine learning techniques is provided, comprising: receiving new 2D image from user input; recognizing multiple objects in the new 2D image by machine learning algorithm; obtaining the hierarchical relations among objects according to the features of the said objects; improving the quality of 3D image according to the hierarchical relations. The implementation of this invention provides a more distinct classification of objects in a 2D image, thereby improving the 2D-to-3D conversion in the computing device.