Abstract: A system for dynamic registration of autonomy using augmented reality can include an augmented reality system, an imaging system, a measuring system, and a computer system. The augmented reality system can be configured to display an augmented representation. The imaging system can be configured to image an anatomical feature of the patient and can generate anatomical imaging data. The measuring system can be configured to measure an anatomical movement of the patient and can generate an anatomical movement data. The computer system can be configured to receive the anatomical imaging and positional data and the anatomical movement data, generate the augmented representation based on the anatomical imaging data, associate the augmented representation with the anatomical movement data, render the augmented representation on the augmented reality system, and selectively update the augmented representation based on the anatomical movement data.

Abstract: A method for use in colourising a three-dimensional (3D) point cloud of an environment, the method including determining timing information indicative of a time of capture of a frame; identifying at least some 3D points of the point cloud in the frame based on the position of the camera and determining a local point cloud that captures a scene in the immediate vicinity of the camera, wherein a visibility check is performed on the local point cloud to determine points in the local point cloud that are visible from the perspective of the camera for a given frame; and determining a candidate colour for the at least some of the 3D points using a colour of a corresponding pixel in the frame extracted from the video data; and, assigning a colour to one or more points of the 3D point cloud using candidate colours obtained from multiple frames.

Abstract: Time of Flight (ToF) depth image processing methods are disclosed for resolving corruption of ToF depth images. In ToF depth imaging, the light can travel paths of different lengths before returning to the pixel. Thus, the light hitting the pixel can have travelled different distances, and the distance obtained from an estimation procedure assuming a single distance may be spurious. Systems and methods are disclosed for including a time-of-flight imager and processor which resolves the multiple paths, and outputs the multiple depths at each pixel.

Abstract: An image signal processor includes a first encoder receiving first image data for pixel data in a graphic image and performing compression on the first image data to generate first compressed data, an alpha map scaler extracting an alpha value ? of the graphic image from the first image data and generating an alpha map for the alpha value ? and a second encoder receiving the alpha map and second image data for pixel data in a video image, performing computation on the second image data using the alpha map to generate multiply data and performing compression on the multiply data to generate second compressed data.

Abstract: A method and system for performing safety-critical rendering of a frame in a tile based graphics processing system. Geometry data for the frame is received, including data defining a plurality of primitives representing a plurality of objects in the frame. A definition of a region in the frame is received, the region being associated with one or more primitives among the plurality of primitives. Verification data is received that associates one or more primitives with the region in the frame. The frame is rendered using the geometry data and the rendering of the frame is controlled using the verification data, so that the rendering excludes, from the frame outside the region, the primitives identified by the verification data.

Abstract: Various implementations disclosed herein include devices, systems, and methods that provide authority transfer of a virtual object in a shared CGR environment. In some implementations, at a first electronic device associated with a first owner having authority to transmit state updates of a virtual object, a state update is transmitted to one or more peers participating in the shared CGR environment associated with the current state of the virtual object by the first electronic device. In some implementations, a handoff message is transmitted to indicate that ownership of the virtual object is being handed off. Then, an acquisition message transmitted by a second electronic device associated with a second owner indicates ownership acquisition of the virtual object by the second owner. The first electronic device accepts state updates of the virtual object transmitted from the second owner based on receiving the acquisition message.

Abstract: A method of generating a three-dimensional (3D) reconstruction of a human includes obtaining at least one colour image and corresponding depth image of a scene comprising a human subject that is at least partially occluded by one or more items. The regions in the at least one colour image corresponding to a human subject are identified. A point cloud of the scene is generated based on the at least one colour image and corresponding depth image. One or more parameters of a parametric model are then adjusted based on the regions of the point cloud identified as corresponding to the human subject. The adjusted parametric model is then used to generate a 3D reconstruction of the human subject; where the parametric model provides an estimate for points in the point cloud corresponding to the occluded parts of the human subject. A corresponding system is also provided.

Abstract: In an image forming apparatus (10), a feature extracted image forming unit (11) includes a line-drawing unit (11A). The line-drawing unit (11A) draws in an image to be processed, for each of a plurality of line-draw groups, a line that passes all the key points included in each of the line-draw groups and has at least one end that is extended to an end of the image to be processed, thereby forming a texture map. Each of the line-draw groups includes at least two key points included in the plurality of predetermined key points.

Abstract: Methods, systems, and wearable extended reality devices for generating a floorplan of an indoor scene are provided. A room classification of a room and a wall classification of a wall for the room may be determined from an input image of the indoor scene. A floorplan may be determined based at least in part upon the room classification and the wall classification without constraining a total number of rooms in the indoor scene or a size of the room.

Abstract: Examples herein describe systems and methods for aligning elements, such as conduit, ductwork, and plumbing within a computer-aided design (“CAD”) application. A plugin can provide an element alignment option on a graphical user interface (“GUI”) of the CAD program. An anchor point from which to align elements is selected in the GUI so that the plugin can choose locations within a structure to run multiple elements in parallel alignment. The system can recommend an alignment plane based on the slopes of the selected multiple elements and provide a direction for a run of the multiple elements. The systems retrieve the specifications and parameters of each individual element to determine its spacing among the run of multiple elements. The run of multiple elements is displayed and manipulated by the plugin via the GUI.

Abstract: Several embodiments of scalable image processing systems and methods are disclosed herein whereby color management processing of source image data to be displayed on a target display is changed according to varying levels of metadata.

Abstract: A method and an apparatus of constructing a chess playing model are disclosed, method includes: acquiring a video image of each chess player; determining a two-dimensional position information for a first expression characterization point in the video image and a marking information for a facial structure characterization point in the first expression characterization point; determining a rotation information for each chess player in a specified direction; reconstructing a three-dimensional reference face model of each chess player so as to generate a three-dimensional target face model of the chess player; reconstructing a three-dimensional target chess player model of the chess player; reconstructing a three-dimensional target chess game model; and reconstructing a three-dimensional target chess playing model.

Abstract: Systems and methods for providing encryption and decryption involving texture warping, comprising: obtaining a visual input; obtaining a private key; generating an encrypted visual representation (visual representation A) based on the private key and the visual input; determining at least one 3D object configured so that the private key is derivable when the visual representation A is mapped to a digital model of the at least one 3D object; transmitting the visual representation A to a second computing device associated with a second user; transmitting a representation of the digital model of the at least one 3D model to the second computing device; and instructing the second computing device so that the second computing device is configured to map the visual representation A to the digital model generated based on the representation of the digital model of the at least one 3D model to extract the private key.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a layer mapping operation are described. A described technique includes receiving a drawing file comprising a first set of layers. A template that defines one or more protocols that control the layer data value aggregation is selected. A set of data values associated with one or more layers in the first set of layers is aggregated in response to applying at least one of the one or more protocols to the drawing file. A second set of layers is generated using the set of data values. A layer mapping output that specifies a second set of layers is generated. The layer mapping output is provided as an input to an application module of a space management program.

Abstract: A system provides the ability to import large engineering 3D models from a primary 3D rendering software into a secondary 3D rendering software that does not have the tools of the resources to render the larger 3D model on its own. The system uses a plugin to combine 3D data from the two software sources, and then return the combined 3D data to the secondary 3D rendering software. Components of the system can be remote or cloud based, and the system facilitates video streaming of 3D rendered models that can be manipulated on any computer capable of supporting a video stream.

Abstract: Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. In some example embodiments, the real-time provision of high quality avatar animation is enabled, at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor.

Abstract: In an embodiment of the invention there is provided a method of visual localization, comprising: generating a plurality of virtual views, wherein each of the virtual views is associated with a location; obtaining a query image; determining the location where the query image was obtained on the basis of a comparison of the query image with said virtual views.

Abstract: A method of tiled rendering is provided which comprises dividing a frame to be rendered, into a plurality of tiles, receiving commands to execute a plurality of subpasses of the tiles and interleaving execution of same subpasses of multiple tiles of the frame. Interleaving execution of same subpasses of multiple tiles comprises executing a previously ordered first subpass of a second tile between execution of the previously ordered first subpass of a first tile and execution of a subsequently ordered second subpass of the first tile. The interleaving is performed, for example, by executing the plurality of subpasses in an order different from the order in which the commands to execute the plurality of subpasses are stored and issued. Alternatively, interleaving is performed by executing one or more subpasses as skip operations such that the plurality of subpasses are executed in the same order.

Abstract: Systems and processes generate a viewing experience by determining location data and movement data of (a) at least one object and (b) at least one participant within an event area. A three-dimensional model of the event area, the participant and the object is determined based upon the location data and the movement data. A viewpoint of a spectator defines an origin, relative to the three-dimensional model, and a direction of the viewing experience. The viewing experience is generated for the viewpoint at least in part from the three-dimensional model to include one or more of augmented reality, mixed reality, extended reality, and virtual reality.

Abstract: In an aspect, an update unit can evaluate condition(s) in an update request and update one or more memory locations based on the condition evaluation. The update unit can operate atomically to determine whether to effect the update and to make the update. Updates can include one or more of incrementing and swapping values. An update request may specify one of a pre-determined set of update types. Some update types may be conditional and others unconditional. The update unit can be coupled to receive update requests from a plurality of computation units. The computation units may not have privileges to directly generate write requests to be effected on at least some of the locations in memory. The computation units can be fixed function circuitry operating on inputs received from programmable computation elements. The update unit may include a buffer to hold received update requests.