Abstract: The disclosure relates to method and system for supervising a plurality of users of XR devices. A problem arises in that a supervisor hoping to assist a user in operating in an XR environment cannot easily obtain a representation of the XR environment which a particular user amongst the plurality of users is currently perceiving. The disclosure addresses this problem by having each XR device and a supervisory device independently determine the position of an XR device. Each XR device provides replica stream data in association with its position, and the user of the supervisory device selects an XR device by selecting its position. By tallying the position in the supervisor's selection of an XR device with the position associated with each replica stream, the replica stream of the XR device selected by the supervisor can be provided to the supervisory device.

Abstract: Apparatuses, systems, and techniques to perform an application programming interface (API) to add one or more graph nodes to a software graph, wherein the API is to cause a child graph node to be added to a software graph based, at least in part, on a dependency type indicated by the API. In at least one embodiment, one or more nodes are added to a graph in accordance to one or more dependency types.

Abstract: The embodiments of the disclosure provide a method for generating a visual content, a host, and a computer readable storage medium. The method includes: in response to determining that the host has connected with a built-in computer of an accommodating space, loading a 3D model associated with the accommodating space, wherein the 3D model at least partially corresponds to a physical structure of the accommodating space; determining a host position of the host within the 3D model and accordingly determining an object position of a predetermined object in the 3D model; and generating the visual content via combining a virtual object with the predetermined object.

Abstract: A method for controlling an artificial intelligence (AI) device for implementing a digital avatar can include receiving an audio signal corresponding to a user query, converting, by a speech-to-text neural network model, the audio signal into a text query, inputting the text query into a large language gesture instruction model to generate high level movement instructions, inputting the text query and the high level movement instructions into an information retrieval model to generate a text response including at least one sentence and digital avatar control information, and inputting the text response into a text-to-speech neural network model to generate an audio response.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for filling gaps in electric grid models are enclosed. A method includes obtaining vector data representing first portions of paths of electric grid wires over a geographic region; converting the vector data to first raster image data that depicts an overhead view of the electric grid wires including a first set of line segments representing the first portions of the paths; processing the first raster image data using a gap filling model; obtaining, as output from the gap filling model, second raster image data including a second set of line segments corresponding to gaps included in the input raster image data and representing second portions of paths of the electric grid wires; and converting the second raster image data to vector data representing the first portions and the second portions of paths of the electric grid wires.

Abstract: Various implementations disclosed herein include devices, systems, and methods that uses blend circuitry to provide a view of live pass-through video with a virtual object including a light-spill effect. For example, a process includes capturing pass-through video of a physical environment. The process further includes capturing virtual content. The process further includes calculating a color from the virtual content. The process further includes controlling the blend circuitry to generate an augmented reality video by blending the pass-through video with the virtual content and by modifying at least one portion of the pass-through video with the calculated color from the virtual content.

Abstract: In some implementations, a method includes: determining a complexity value for first image data associated with of a physical environment that corresponds to a first time period; determining an estimated composite setup time based on the complexity value for the first image data and virtual content for compositing with the first image data; in accordance with a determination that the estimated composite setup time exceeds the threshold time: forgoing rendering the virtual content from the perspective that corresponds to the camera pose of the device relative to the physical environment during the first time period; and compositing a previous render of the virtual content for a previous time period with the first image data to generate the graphical environment for the first time period.

Abstract: The present disclosure discloses an image processing method, an apparatus, an electronic device, and a storage medium. The method includes: determining at least one target limb key point of a current video frame; determining at least one current effect key point according to the at least one target limb key point and historical limb key points of at least one historical video frame adjacent to the current video frame; obtaining historical effect key points of the at least one historical video frame according to preset effect parameters, and determining, according to the at least one current effect key point and the historical effect key points, at least one group of target effects matching the preset effect parameters; and determining a target video frame corresponding to the current video frame based on the at least one group of target effects.

Abstract: Disclosed in examples of the disclosure are a method, apparatus, device, and storage medium for processing image. The method includes: extracting facial feature information of a first character appearance image and structural feature information of a second character appearance image (S110); inputting the facial feature information and the structural feature information into a first character appearance fusion model, and obtaining a third character appearance image (S120); training a second character appearance fusion model based on the first character appearance image, the second character appearance image and the third character appearance image (S130); and inputting a source character appearance image and a target character appearance image into the trained second character appearance fusion model to obtain a new character appearance image (S140).

Abstract: Augmented reality (AR) methods are provided for guiding user movement within an AR environment. The methods involve calculating an angle between the user's current viewing direction and a target location, and determining if this angle exceeds a visibility threshold of an AR display device. A guidance vector is computed to account for user movement, and a visual navigation aid corresponding to this vector is generated to direct the user towards the target. The visual aid may be an arrow or pointer displayed on a heads-up display (HUD). The guidance vector is adjusted by a correction factor to prioritize lateral head movements and may include additional visual elements to indicate the required rotation. The system includes at least one processor and memory to execute these operations. A computer-readable storage medium contains instructions for executing the method, facilitating real-time updates of the navigation aid as the user's viewing direction changes.

Abstract: A method, apparatus, non-transitory computer readable medium, and system for image processing include obtaining an outline image and an input prompt, where the outline image includes an outline of a region and the input prompt indicates content for the region, generating a mask based on the outline image, where the mask indicates the region within the outline, generating a preliminary image based on the mask, where the preliminary image includes noise in the region indicated by the outline, and generating a synthetic image based on the input prompt, the mask, and the preliminary image, where the synthetic image depicts the content in the region indicated by the outline. A vectorized image is generated based on the synthetic image.

Abstract: An electronic apparatus according to the present invention includes a processor, and a memory soring a program which, when executed by the processor, causes the electronic apparatus to execute acquisition processing to acquire a live view image, and execute display control processing to perform geometric transformation for a display range, which is a partial region of the live view image, and to perform control so as to display a geometrically transformed image for display, where the display range is changeable, wherein in the display control processing, control is performed so as to further display an item which makes the region displayed in the live view image identifiable.

Abstract: A method, system, and non-transitory computer readable medium includes providing, by the computing device, a hierarchal graphical user interface with selectable attributes and visualization options in response to a prompt from a client device. The hierarchal graphical user interface can be generated prior to the transmission to the client device. Next, the method can include generating, by the computing device, a report by inputting the prompt, selected attributes, and a selected visualization option into a machine learning model to generate the report. The machine learning model can be configured to use marketing data, building data, or combinations thereof for the generation of the report. Then, the method can include updating and providing, by the computing device, a modified hierarchal graphical user interface to the client device, where the modified hierarchal graphical user interface is the hierarchal graphical user interface modified to comprise the report.

Abstract: A system and associated methods perform real-time analytic and non-iterative generation of a splat representation at different levels-of-detail (LoDs). The system receives a splat representation of a three-dimensional (3D) asset. The system partitions the 3D space of the splat representation into voxels and determines directions and amounts with which the set of splats within each voxel spread out from a centroid that is derived based on positions of the splats in that voxel. The system defines a substitute splat for each voxel based on the one or more directions and amounts that are determined for the set of splats in that voxel and generates the splat representation at a reduced LoD based on the substitute splat that is defined for each voxel.

Abstract: A text-to-image prompt is processed using a text-to-image machine learning model to obtain a non-immersive (e.g., rectilinear image). The non-immersive image may be enhanced by a superresolution machine learning model and processed with a monoscopic depth estimation model to obtain a depthmap. The non-immersive image and the depthmap may be converted to an immersive projection (e.g., F-theta) and corresponding depth map. The immersive projection may be out-painted. The immersive projection may be used to generate video with simulated camera movement, output on a VR headset, and/or processed to remove a background layer and displayed on an AR headset, or on an holographic glasses-free three-dimensional display.

Abstract: A system manages virtual content in association with a purchaser of the virtual content, as the virtual content management, when a code corresponding to the virtual content is detected by a terminal, further associates a feature amount acquired from a real space by the terminal with the virtual content, and controls the terminal to project the virtual content into a field of view of a user of the terminal.

Abstract: Embodiments herein disclose a method for facilitating a privacy-aware representation in a system. The method comprises determining using a content analyzer a layout of a scene. Thereafter, one or more objects in the scene is identified using the content analyzer to define a relationship between the objects. A privacy status to be tagged to the one or more identified objects is inferred by using a machine learning model. At least one object is processed based on the privacy status inferred. A privacy-aware representation of the scene is rendered, wherein the privacy-aware representation displays the scene with at least one processed object.

Abstract: Embodiments for rendering an operative guidance overlay in association with a patient are disclosed. A method includes receiving image data indicating an anatomical structure of the patient and a structure of operative instruments; generating virtual models based on the image data; receiving sensor data associated with a user, the operative instruments, or the patient; dynamically generating guidance overlay data associated with the anatomical structure of the patient, or the operative instruments based on the virtual models and the sensor data; and rendering the operative guidance overlay in association with the patient based on the guidance overlay data using a wearable augmented reality interface device. The virtual models include a virtual anatomical model of the anatomical structure of the patient, or virtual instrument models associated with the operative instruments.

Abstract: Method, system, and computer-readable storage media for image conversion. A first image in a raster format is preprocessed to form a second image. Further, the second image is converted into grayscale to create a third image. Furthermore, the third image is denoised and smoothened to create a fourth image. A fifth image is created based on the fourth image by at least adding borders to objects in the third image. Further, a layering of the objects is first determined within the fifth image. Also, the objects in the fifth image are highlighted to create a sixth image. A graph schema is generated based on the fifth and/or sixth image. Based on the graph schema, edges of the objects within the sixth image are identified. Further, the sixth image is ungrouped based on the identified edges of the objects, the ungrouping generates an individual vector image for each of the objects.

Abstract: Methods and systems are disclosed for generating video by applying a template to various content items. The methods and systems select, by an interaction application, a video generation template comprising instructions for combining a set of content items into a video using one or more augmented reality (AR) elements. The methods and systems identify a subset of content items from a plurality of previously captured content items and modify one or more content items of the identified subset of content items based on the AR elements of the video generation template. The methods and systems generate a video comprising a collection of content items including the identified subset of content items and the modified one or more content items based on the instructions of the video generation template.