Abstract: A landmark detection system can more accurately detect landmarks in images using a detection scheme that penalizes for dispersion parameters, such as variance or scale. The landmark detection system can be trained using both labeled and unlabeled training data in a semi-supervised approach. The landmark detection system can further implement tracking of an object across multiple images using landmark data.

Abstract: Systems and methods are described for replacing a background portion of an image. An illustrative method includes receiving a first image, identifying a background portion of the first image and a subject portion of the first image, retrieving metadata associated with the first image, determining, based on the metadata, a geographic location where the first image was captured, retrieving a plurality of other images captured at the geographic location, selecting a second image from the plurality of other images, wherein the second image is associated with metadata indicating that the second image was captured during a predetermined time period, and generating for display a third image comprising the subject portion of the first image placed over the second image.

Abstract: A method of generating an image file of a high resolution 3D garment model on a 3D body model, comprising the steps of: (i) acquiring at least three 2D images of a garment on a mannequin, wherein the at least three 2D images capture a 360° azimuthal angle range of view of the garment, including a texture of the garment; (ii) creating a simplified 3D garment model using the 2D images of the garment; (iii) simulating the smooth and simplified 3D garment model on the 3D body model; (iv) deforming and rendering the high-resolution garment texture on the simulated smooth and simplified 3D garment model on the 3D body model, and (v) generating an image file of the 3D body model, the image file including the deformed and rendered high-resolution garment texture, on the simulated smooth and simplified 3D garment model, on the 3D body model.

Abstract: Systems and methods providing for determining physical location of a device of a user of an augmented reality environment corresponding to a physical space. The systems and methods involve requesting and receiving a list of participating users having a GPS location within a predetermined radius of a first device; sending advertising and scanning beacons, via a first wireless network, to generate a second list of devices present in the physical space; performing simultaneous localization and mapping (SLAM) using the participating devices of the second list; generating a third list based at least partly on a Bluetooth connection between the one or more participating devices of the second list; and identifying the participating devices of the third list.

Abstract: There is provided a display control system including a plurality of display units, an imaging unit configured to capture a subject, a predictor configured to predict an action of the subject according to a captured image captured by the imaging unit, a guide image generator configured to generate a guide image that guides the subject according to a prediction result from the predictor, and a display controller configured to, on the basis of the prediction result from the predictor, select a display unit capable of displaying an image at a position corresponding to the subject from the plurality of display units, and to control the selected display unit to display the guide image at the position corresponding to the subject.

Abstract: Techniques are described for virtual representation creation and display. Processing circuitry may identify substantially transparent pixels in a virtual hairstyle, identify a first set of pixels that are away from the identified substantially transparent pixels, increase an opacity level for a second set of pixels that excludes the first set of pixels by a first amount, and generate the virtual hairstyle based on the first set of pixels and the second set of pixels having the increased opacity level. With the generated virtual hairstyle, processing circuitry of a personal computing device may blend, in a first pass, one or more pixels of the version of the generated virtual hairstyle having an opacity level greater than or equal to a threshold opacity level, and blend, in a second pass, one or more pixels of the version of the generated virtual hairstyle having an opacity level less than the threshold opacity level.

Abstract: A virtual reality experience apparatus includes: a displaying device configured to provide an experiencing user with a virtual reality image; and a riding device configured to provide the experiencing user with a motion, wherein the riding device includes: a riding part providing the experiencing user with a ridable space, and a gyro mechanism generating a pitching motion and a rolling motion of the riding part, wherein the gyro mechanism includes: a base structure having a pair of support columns disposed apart from each other, a pitching mechanism rotatably mounted on the pair of support columns to be rotated with respect to a pitching axis extending between the pair of support columns, and a rolling mechanism rotatably mounted on the pitching mechanism to be rotated with respect to a rolling axis perpendicular to the pitching axis.

Abstract: The disclosed computer-implemented method may include tracking (1) a position of a primary real-world object within a real-world environment via a primary tracking method, and (2) a position of a secondary real-world object within the real-world environment via a secondary tracking method. The method may further include presenting (1) a primary virtual object at a position within an artificial environment corresponding to the tracked position of the primary real-world object, and (2) a secondary virtual object at a position within the artificial environment corresponding to the tracked position of the secondary real-world object. The method may further include (1) detecting an interaction of the primary real-world object with the secondary real-world object, and (2) transitioning to tracking the position of the primary real-world object via the secondary tracking method. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Given a parcel of land that is regulated by city zoning rules, the system and method described uses a combination of rule based coded and machine learning to parametrically create geometry for the maximum or optimal buildable envelope with the least amount of regulation.

Abstract: A path tracing system in which the traversal task is distributed between one global acceleration structure, which is central in the system, and multiple local acceleration structures, distributed among cells, of high locality and of autonomous processing. Accordingly, the centrality of the critical resource of accelerating structure is reduced, lessening bottlenecks, while improving parallelism.

Abstract: This application provides a method for controlling a virtual object performed at an electronic device: obtaining a current location of a virtual object in a virtual scene; determining whether the current location is located outside an associated area of the virtual object; in accordance with a determination that the current location of the virtual object is outside the associated area of the virtual object: determining a current state of the virtual object at the current location; in accordance with a determination that the virtual object is performing an action of a first state, controlling the virtual object to return to a pre-specified location within the associated area after the virtual object completes the action; and in accordance with a determination that the virtual object is in a second state: controlling the virtual object to return to the pre-specified location within the associated area after waiting a predetermined time period.

Abstract: A projection display device includes an image data control unit that controls image data to be input to a light modulation unit, and a situation determination unit that determines, in a state where an automated driving mode is set, whether or not a situation has occurred where an operation device mounted in a vehicle and used for driving needs to be operated. When it is determined that the situation has occurred where the operation device needs to be operated, the image data control unit inputs, to a driving unit, first image data for displaying images corresponding to a plurality of operation devices in a positional relationship corresponding to an arrangement of the plurality of operation devices and displaying, in an emphasized manner, the image corresponding to the operation device that needs to be operated, and displays an operation assisting image that is based on the first image data.

Abstract: Embodiments of the disclosure disclose a system, method and apparatus for displaying information. A specific embodiment of the method comprises: acquiring currently displayed information, the currently displayed information including an image; associating an augmented reality AR display identifier with the currently displayed information, in response to a preset object in a preset object set existing in the image; displaying the image associated with an AR play identifier, in response to receiving a request for browsing the currently displayed information associated with the AR display identifier from a user; acquiring AR image data of the preset object existing in the image from a server, in response to receiving a request for browsing the image associated with the AR play identifier from the user; and displaying an AR image of the preset object existing in the image based on the AR image data of the preset object existing in the image.

Abstract: Techniques are presented for constructing a digital representation of a physical environment. In some embodiments, a method includes obtaining image data indicative of the physical environment; receiving gesture input data from a user corresponding to at least one location in the physical environment, based on the obtained image data; detecting at least one discontinuity in the physical environment near the at least one location corresponding to the received gesture input data; and generating a digital surface corresponding to a surface in the physical environment, based on the received gesture input data and the at least one discontinuity.

Abstract: A generation apparatus is configured to generate a virtual viewpoint image based on a plurality of images captured by a plurality of cameras for imaging a field from a plurality of different directions, the generation apparatus including an acquisition unit configured to acquire, based on a three-dimensional model of at least a portion of the field, correspondence information indicating correspondence between a coordinate of an image captured by at least one of the plurality of cameras and a coordinate related to a simple three-dimensional model less accurate than the three-dimensional model, and a generation unit configured to generate a virtual viewpoint image according to designation about a position and an orientation of a virtual viewpoint, by using an image captured by one or more of the plurality of cameras and the correspondence information acquired by the acquisition unit.

Abstract: A data visualization system creates a visual representation of data. The visual representation of data is provided in a form that enables an end user to adjust variable data upon which one or more determined data elements are based using an input device. The adjustment of the variable data is detected, and the visual representation of the data is refreshed based on the detected adjustment of the variable data.

Abstract: An image signal processing device of the present disclosure includes a luminance correction section that performs, on a basis of information on a maximum output luminance value in a display section, luminance correction on an image signal to be supplied to the display section, the maximum output luminance value being variable.

Abstract: Video noise reduction for a video augmented reality system is provided. A head mounted display includes a display unit; a camera for generating frames of display data. A frame store is provided for storing previous frames of displayed information that was sent to the display unit; and a motion processor is provided in communication with the camera, display unit, and the frame store. The motion processor is operable to: identify an area of interest in a current frame of display data; match the area of interest to similar areas in previous frames stored in the frame store; rotate and translate the matched areas of interest from the one or more previous frames stored in the frame store to match the area of interest in the current frame; and average the prior matched areas of interest with the current area of interest to generate a displayed area of interest.

Abstract: A method and system for generating an augmented reality experience without a physical marker. At least two frames from a video stream are collected and one of the frames is designated as a first frame. The graphical processor of a device prepares two collected frames for analysis and features from the two collected frames are selected for comparison. The central processor of the device isolates points on a same plane as a tracked point in the first frame and calculates a position of a virtual object in a second frame in 2D. The next frame from the video stream is collected and the process is repeated until the user navigates away from the URL, webpage or when the camera is turned off. The central processor renders the virtual object on a display of the device.

Abstract: A program for causing a computer to execute: receiving an instruction to change a position and a direction of a viewpoint disposed in a virtual space from a user; controlling a viewpoint to change the position and the direction of the viewpoint in response to the instruction; rendering a spatial image that depicts an aspect of an interior of the virtual space on the basis of the position and the direction of the viewpoint; and switching over between a first mode of changing the direction of the viewpoint about the position of the viewpoint and a second mode of changing the position and the direction of the viewpoint about an object of interest to which the user pays attention in the virtual space in a case of receiving an instruction to change the direction of the viewpoint from the user at a time of controlling the viewpoint.