Abstract: A wearable terminal apparatus to be worn by a user for use includes at least one processor, a camera, and a communication unit. The camera images a space as a visible region of the user. The communication unit performs data communication with an external device to be used by a remote instructor. The at least one processor transmits an image obtained by the camera to the external device via the communication unit. The at least one processor receives instruction information related to an instruction to generate an instruction image via the communication unit, the instruction being made based on the image in the external device. The at least one processor causes a display unit to display the instruction image, the instruction image being visually recognized at a position based on the received instruction information in the space. The at least one processor accepts a user operation to change the displayed instruction image and updates display of the instruction image in accordance with the user operation.

Abstract: The application discloses a method, electronic device, and storage medium for image processing, which includes: in response to determining that the trigger of an effect display function is detected, adding a virtual model to a collected image to be processed to obtain a presentation video frame; magnifying-displaying an image area of the virtual model in the presentation video frame, and processing the virtual model into a target three-dimensional effect model in response to determining that a magnification stop condition is reached; fusing the target three-dimensional effect model and a target object in the image to be processed to present a target video frame.

Abstract: Systems and methods for occluding virtual objects in an augmented reality environment are described. A method includes generating a distance map associated with a physical object, determining a location of a virtual object in an artificial-reality environment, determining, based at least in part upon the distance map and the location of the virtual object, a first portion of the physical object that is closer than a first portion of the virtual object from the viewpoint of the user, determining a second portion of the virtual object that is not obscured by the physical object from the viewpoint of the user, and rendering a display image. The display image comprises a first set of pixels corresponding to the first portion of the physical object in a first state, and the display image comprises a second set of pixels corresponding to the second portion of the virtual object in a second state.

Abstract: Described is a system for overlaying visual content onto a real-world object by identifying a prompt of a user indicating a user's intent, accessing an image template, wherein the image template includes placement of features within the image template, and processing a combination of data associated with the image template and the prompt using a generative machine learning model to generate a first populated image template in which one or more portions of the image template are populated with visual content representing the user's intent. The system then proceeds to access an image depicting a real-world object and overlay the first populated image template that includes the visual content representative of the user's intent on at least a portion of the real-world object based on the placement of the features of the image template.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for annotation of 3D models with signs of use that are visible in 2D images. In one aspect, methods are performed by data processing apparatus. The methods can include projecting signs of use in a relatively larger field of view image of an instance of an object onto a 3D model of the object based on a pose of the instance in the relatively larger field of view image, and estimating a relative pose of the instance of the object in a relatively smaller field of view image based on matches between the signs of use in the relatively larger field of view image and the same signs of use in the relatively smaller field of view image.

Abstract: This application provides an image rendering method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product. The method comprises the following steps: acquiring texture data of a virtual object; performing differential fitting processing on the texture data to obtain fitted texture data; baking the fitted texture data into a texture image to obtain a rendered texture image; and performing, based on the rendered texture image, image rendering processing corresponding to the virtual.

Abstract: A system for the recommendation of a makeup look to a user in response to data corresponding to a smart cosmetic device, wherein the recommended makeup look is presented to a user for application using the smart cosmetic device. The smart cosmetic device collects user behavioral history such as cosmetic substance usage (e.g., color and formula of a particular cosmetic substance), design configuration (e.g., spray canister, pen, and so on), and usage pattern (e.g., frequency of use for a particular cosmetic substance at a particular time of the day, a particular day of the week, or a particular event). Data associated with user behavioral history is processed by the system to generate at least one user-personalized makeup look recommendation for presentation to the user.

Abstract: A technique for rendering is provided. The technique includes determining a level of detail for a shade space texture and a screen space; shading the shade space texture having a resolution based on the level of detail; and for a reconstruction operation, performing sampling from the shade space texture, the sampling including a high frequency attenuation of samples of the shade space texture.

Abstract: A multi-viewer extended reality (XR) streaming method of streaming XR images between a plurality of XR application instances and a plurality of XR devices is described. The multi-viewer XR streaming method comprises the steps of streaming, by means of a first XR application instance of the plurality of XR application instances, first XR images to at least one XR device, wherein the first XR images correspond to virtual content viewed from a first spectator position; determining a position of the at least one XR device relative to the first spectator position; and reprojecting, by means of the at least one XR device, the first XR images based on the determined position of the at least one XR device. Further, an XR streaming system is described.

Abstract: Techniques are described for moving and aligning groups of teeth, including the teeth of an entire arch, for orthodontic treatment planning. One or more 3D models each representing one of a plurality of the patient's teeth may be analyzed to identify feature points that represent clinically relevant reference points on the tooth. An arch shape may be generated based on the feature points. One or more control points, which characterize the path of the arch shape, may then be generated (e.g., from the identified feature points). A user may provide input that modifies the positions of one or more of the control points to adjust the arrangement of teeth, thereby producing a new arch shape, and new positions of the teeth may be determined according to the new arch shape.

Abstract: In various embodiments, a computer animation application automatically solves inverse kinematic problems when generating object animations. The computer animation application determines a target vector based on a target value for a joint parameter associated with a joint chain and at least one of a target position or a target orientation for an end-effector associated with the joint chain. The computer animation application executes a trained machine learning model on the target vector to generate a predicted vector that includes data associated with multiple joint parameters associated with the joint chain.

Abstract: A customized computer-generated virtual environment corresponding to an environment familiar to a user for providing items in locations that are familiar to the user based on corresponding real-world environments and locations is provided. In association with the customized computer-generated virtual environment, a method may include generating an interactive virtual environment, wherein the generated interactive virtual environment includes virtual rooms and virtual areas based on the familiar environment. The method may also include identifying an item and a location of the item in the familiar environment, and correlating and associating the identified item with a corresponding location in the generated interactive virtual environment. The method may further include identifying and retrieving different items having a determined similarity to the identified item.

Abstract: A method of operating a service providing device includes: collecting a source image and processing face warping of the collected source image to transform the collected source image into a warping image based on a benchmark image; constructing, using the face warped source image, a style database to which style information of the source image is mapped; and providing a style recommendation service based on style transfer using the style database. The providing includes: performing face warping on a user image input from a user terminal; performing style transfer of the face warped source image in response to the face warped user image; and processing face reverse warping of the image subjected to the style transfer to output as a virtual style synthesis image.

Abstract: Disclosed is a method for encoding 3D volumetric data to estimate pose and shape data from 3D volumetric data, generate a 3D estimation model by applying the estimated data to a 3D template model, and encode residual data of the 3D volumetric data together with the 3D estimation model, and the method includes: (a) receiving 3D volumetric data; (c) estimating a 3D pose from the 3D volumetric data; (d) estimating a 3D shape from the 3D volumetric data; (e) generating a 3D estimation model by modifying a predefined 3D template model; (f) calculating a residual of the 3D volumetric data with respect to the 3D estimation model; and (h) generating the pose estimation data, the shape estimation data and data on the residual as transmission data. Accordingly, an amount of data in the 3D volumetric model is significantly reduced and complexity is reduced.

Abstract: The following relates generally to light detection and ranging (LIDAR) and artificial intelligence (AI). In some embodiments, a system: receives light detection and ranging (LIDAR) data generated from a LIDAR camera; receives preexisting utility line data; and determines a location of the utility line based upon: (i) the received LIDAR data, and (ii) the received preexisting utility line data.

Abstract: Systems and methods are disclosed for determining optical measurements for adjusting virtual try-on glasses. The method includes receiving a digital input including an image of a user's face and a known-sized object, wherein the known-sized object is positioned against a screen adjacent to a camera of a user device. A plurality of instructions is generated in a user interface of the user device for tracking eye movements of the user, wherein the plurality of instructions advises the user to look at the first feature of the known-sized object, a second feature of the known-sized object, and into a distance beyond the known-sized object. A scaled reconstruction of the user's face and/or a recommendation on virtual try-on glasses is generated based on the tracking of the eye movements and/or calculations based on equations.

Abstract: Augmented reality systems provide graphics over views from a mobile device for both in-venue and remote viewing of a sporting or other event. A server system can provide a transformation between the coordinate system of a mobile device (mobile phone, tablet computer, head mounted display) and a real world coordinate system. Requested graphics for the event are displayed over a view of an event. In a tabletop presentation, video of the event can be displayed with augmented reality graphics overlays at a remote location.

Abstract: Provided is an electronic device including a first processor configured to generate frames by performing render operation stages based on graphics data, a memory configured to store an application to obtain information corresponding to the first processor, a display, and a second processor electrically connected to the first processor, the memory, and the display, wherein the second processor is configured to execute the application, obtain render stage information corresponding to the frames through the executed application, extract first render stage information corresponding to a first frame, among the frames, from the obtained render stage information, process the extracted first render stage information, and control the display to display a user interface (UI) screen including the processed first render stage information.

Abstract: Embodiments of the present disclosure relate to methods, systems, and computer program products for rendering a three-dimensional anatomical model in a virtual or augmented reality device. In various embodiments, a method includes reading, at a remote server, a three-dimensional imaging study from a data store, where the three-dimensional imaging study includes a plurality of two-dimensional slices of at least one anatomical structure, optionally performing segmentation, at the remote server, on each of the plurality of two-dimensional slices, generating, at the remote server, a volumetric model of the at least one anatomical structure based on the plurality of two-dimensional slices, scaling, at the remote server, the volumetric model according to one or more display parameters of a virtual or augmented reality device, receiving, at the virtual or augmented reality device, the scaled volumetric model; and rendering, at the virtual or augmented reality device, the scaled volumetric model.

Abstract: A three-dimensional computer-generated environment can be presented to a user. The user can create a virtual representation of a real-world object within the computer-generated environment by directing an input device towards the real-world object and tracing contours of the real-world object. The virtual representation can include voxels. The user can edit the virtual representation or create a new virtual object formed of voxels by depositing or removing voxels at virtual locations within the computer-generated environment based on selection inputs, release inputs, and optionally movement inputs detected by the input device. In some cases, the user can provide inputs via another input source, such as a hand of the user, that are detected by additional sensors or devices.