Abstract: A system for real-time updates to a display based upon the location of a camera or a detected location of a human viewing the display or both is disclosed. The system enables real-time filming of an augmented reality display that reflects realistic perspective shifts. The display may be used for filming, or may be used as a “game” or informational screen in a physical location, or other applications. The system also enables the use of real-time special effects that are centered upon an actor or other human to be visualized on a display, with appropriate perspective shift for the location of the human relative to the display and the location of the camera relative to the display.

Abstract: A method comprising: in response to a determination that a user is not consuming or not fully consuming virtual content, rendering to the user, a real-time notification in response to real-time virtual content consumable by the user, wherein the real-time notification directs a user to adopt a particular orientation in the real space for starting or augmenting consumption, of the real-time virtual content.

Abstract: The proposed approach is a system and method that allows a user to calculate a 3D model for each of his or her feet using a simple reference object and a mobile computing device with one or more cameras and/or one or more sensors. The mobile computing device moves around the user's feet to scan and/or capture data of his or her feet via the camera and/or the sensors. The captured sensor data is then processed by the mobile computing device to create two sets of 3D (data) point sets (also referred to as “point clouds”). These point clouds are then matched to a 3D model of an average foot to establish a correspondence between the point clouds and the 3D model. Once the correspondence is established, the mobile computing device is configured to fit one or more morphable models to the user's feet.

Abstract: Systems and methods for utilizing living entities as markers for virtual content in an augmented reality environment are discussed herein. The virtual content may comprise objects, surfaces, textures, effects, and/or other content visibly manifested in views of the augmented reality environment. In some implementations, the virtual content may comprise an avatar and/or other full- or partial-body virtual content object depicted based on the living entity. A living entity and multiple linkage points for the living entity may be detected within the field of view of a user. Based on the arrangement of the linkage points, virtual content may be rendered and appear superimposed over or in conjunction with a view of the living entity in the augmented reality environment. In some implementations, the rendering of virtual content in the augmented reality environment may be triggered by the arrangement of the multiple linkage points for a given living entity.

Abstract: In rendering, in a virtual reality (VR) space, a web page including a tangible object, an area for a user input is displayed on a browsing window of the web page as an area corresponding to a corresponding tangible object with respect to tangible objects. An interested object according to the user input among the tangible objects is displayed on another browsing window in the VR space by separating the interested object from the web page.

Abstract: The disclosed embodiments include computer-implemented devices, systems, and methods that support image processing services. In an embodiment, a server may match a partial image received from a terminal with stored candidate image in the memory, and upon identification of a match, transmit information identifying the matched candidate image to the terminal.

Abstract: Systems and methods that provide visualization of networks. Data is input into a table structure that represents any hierarchy of entities, relationships and their attributes. The content of the table is processed to extract the entities, relationships and their attributes. These are turned into nodes, edges and a visual representation of their attributes using color gradients, categorical colors, shapes, thickness, text labels, etc.

Abstract: The invention presents a system and a method for 3D human reconstruction using a compact kit of depth cameras. Instead of using complex and expensive devices as in traditional methods, the proposed system and method employs a simple, easy-to-install system to accurately collect the human body shape. The generated model is capable of moving thanks to a skeleton system simulating the human skeleton. The proposed system includes four blocks: Data Collection Block, Point Cloud Standardization Block, Human Digitization Block and Output Block. The proposed method includes five steps: Point Cloud Collecting, Point Cloud Filtering, Point Cloud Calibrating, Point Cloud Optimizing and 3D Human Model Generating.

Abstract: Disclosed is an editing system for postprocessing three-dimensional (“3D”) image data to realistically recreate the effects associated with viewing or imaging a represented scene with different camera settings or lenses. The system receives an original image and an edit command with a camera setting or a camera lens. The system associates the selection to multiple image adjustments. The system performs a first of the multiple image adjustments on a first set of 3D image data from the original image in response to the first set of 3D image data satisfying specific positional or non-positional values defined for the first image adjustment, and performs a second of the multiple image adjustments on a second set of 3D image data from the original image in response to the second set of 3D image data satisfying the specific positional or non-positional values defined for the second image adjustment.

Abstract: The described technology regards an augmented reality system and method for estimating a position of a location of interest relative to the position and orientation of a display, including receiving and selectively filtering a plurality of measurement vectors from a rate-gyroscope. Systems of the described technology include including a plurality of sensors, a processing module or other computation means, and a database. Methods of the described technology use data from the sensor package useful to accurately render graphical user interface information on a display.

Abstract: Embodiments described herein provide a processing apparatus comprising compute circuitry to generate neural network data for a convolutional neural network (CNN) and write the neural network data to a memory buffer. The compute circuitry additionally includes a direct memory access (DMA) controller including a hardware codec having encode circuitry and a decode circuitry. The DMA controller reads the neural network data from the memory buffer, encode the neural network data via the encode circuit, writes encoded neural network data to a memory device coupled with the processing apparatus, writes metadata for the encoded neural network data to the memory device coupled with the processing apparatus, and decodes encoded neural network data via the decode circuit in response to a request from the compute circuitry.

Abstract: A method includes obtaining scene data, wherein the scene data includes image data of a scene and depth data of the scene, and the depth data includes depth measurement values of points of a point cloud. The method further includes defining a first detection area, wherein the first detection area includes a spatially defined subset of the scene data, defining a plane model based on points of the point cloud within the first detection area, and defining a plane based on the plane model. The method includes determining at least one value of a usable size of the plane based on points of the point cloud, comparing at least one value of a characteristic size of a digital object to the at least one value of the usable size of the plane, and generating a display including the digital object positioned upon the plane based on the plane model.

Abstract: Damaging a device that is not compatible with a functional extension is to be avoided. A signal is transmitted to an external device through a transmission channel. A data block containing capability information indicating existence/non-existence of compatibility with an extended function is received from the external device through the transmission channel. A layer field that indicates the connection layer is provided in this data block. A check is made to determine whether all the devices existing in the path are compatible with the extended function based on the value of the layer field provided in the data block, and the contents of the transmission signal are then determined.

Abstract: Disclosed is a signal processing device and an image display apparatus including the same. The signal processing device includes: a linear tone mapper configured to perform linear tone mapping on a part of an input image; a non-linear tone mapper configured to perform non-linear tone mapping on another part of the input image; and a combiner configured to combine an output from the linear tone mapper and an output from the non-linear tone mapper. Accordingly, it is possible to map the dynamic range of an input image to a display.

Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.

Abstract: Methods and graphics processing systems render primitives using a rendering space which is subdivided into a plurality of regions. Geometry processing logic performs a geometry processing phase which determines, for each of a plurality of primitives which are present in a region, whether the primitive totally covers the region; and stores data for the primitives which are present in the region, wherein the stored data comprises, for each of the primitives which are determined to totally cover the region, data to indicate total coverage of the region. Rendering logic performs a rendering phase for rendering primitives within the region.

Abstract: A non-transitory storage medium stores instructions executable by an information processing device including an operation device and a display. The instructions cause the information processing device to: display a first image; display a cropping frame for cropping of the first image when the operation device accepts a user operation for displaying the cropping frame in a state in which the first image is displayed; rotate the first image about a center of the cropping frame when the operation device accepts a user operation for rotating the first image in a state in which the first image and the cropping frame are displayed; and rotate the first image about a center of the first image when the operation device accepts a user operation for rotating the first image in a state in which the first image is displayed, and the cropping frame is not displayed.

Abstract: An electronic device and method of preservation of geometry details in tracked meshes is provided. A set of three-dimensional (3D) scans and a sequence of tracked meshes of an object of interest are acquired. The sequence of tracked meshes comprises a set of tracked meshes which temporally corresponds to the set of 3D scans. Based on differences between the set of tracked meshes and the set of 3D scans, a set of displacement maps is generated. A plurality of vectors is computed, each of which includes surface tension values associated with mesh vertices of a corresponding tracked mesh. Based on the set of displacement maps and a corresponding set of vectors, a neural network is trained on a task of displacement map generation. The trained neural network model is applied on the plurality of vectors to generate displacement maps. Each tracked mesh is updated based on a corresponding displacement map.

Abstract: A method and system for performing graphics processing is provided. The method and system includes storing stencil buffer values in a stencil buffer; generating either or both of a reference value and a source value in a fragment shader; comparing the stencil buffer values against the reference value; and processing a fragment based on the comparing the stencil buffer values against the reference value.

Abstract: Apparatus and method for processing motion blur operations. For example, one embodiment of a graphics processing apparatus comprises: a bounding volume hierarchy (BVH) generator to build a BVH comprising hierarchically-arranged BVH nodes based on input primitives, at least one BVH node comprising one or more child nodes; and motion blur processing hardware logic to determine motion values for a quantization grid based on motion values of the one or more child nodes of the at least one BVH node and to map linear bounds of each of the child nodes to the quantization grid.