Abstract: An example operation may include one or more of establishing a network connection between a computing system and one or more external sources over a computer network, receiving a request from a user via a software application on a user device, collecting data about the user from the one or more external sources via the established network connection, executing a machine learning model on the collected data about the user to determine a goal of the user, and displaying an image of the goal via a user interface of the software application.

Abstract: A method for manipulating laparoscopic images taken during a laparoscopic procedure using a video laparoscope. The method including: analyzing the laparoscopic images relative to visibility of an object; calculating a placement of a pre-generated 3D model of the object relative to the location of the object in the laparoscopic images; generating a visual representation of the 3D model; comparing at least one of color information and brightness information of the visual representation of the 3D model and of the laparoscopic images at the location of the 3D model and adjusting the representation of the 3D model based on the comparison in regions where the difference is below a predefined threshold; and generating composite images using the laparoscopic images and the adjusted representation of the 3D model.

Abstract: A portable device for projecting medical data of a patient, including a housing, wireless technology that allows the exchange of data between different electronic devices, a projector that can project a light beam image of the data received from the wireless technology onto a desired surface away from the housing, and a coupler that couples the projector to the housing and enables the projector to tilt and/or swivel and/or rotate so that the location of the projected light beam image can be changed, e.g., to display on a ceiling or desired wall. The medical data projected can be glucose level data. The apparatus enables a person to easily obtain information on their glucose levels when they wake at night without having to access an electronic device to obtain the information.

Abstract: A method of generating a high dynamic range (HDR) image is provided that includes capturing a long exposure image and a short exposure image of a scene, computing a merging weight for each pixel location of the long exposure image based on a pixel value of the pixel location and a saturation threshold, and computing a pixel value for each pixel location of the HDR image as a weighted sum of corresponding pixel values in the long exposure image and the short exposure image, wherein a weight applied to a pixel value of the pixel location of the short exposure image and a weight applied to a pixel value of the pixel location in the pixel long exposure image are determined based on the merging weight computed for the pixel location and responsive to motion in a scene of the long exposure image and the short exposure image.

Abstract: The present disclosure provides world-controlled augments and application-controlled augments. World-controlled augments can be controlled directly by a shell in the artificial reality environment. To allow even inexperienced users to develop world-controlled augments, a world-controlled builder system is provided. Application-controlled augments may be resource intensive (e.g., using eye-tracking, social-media tie-ins, etc.), may support complicated interactions among themselves, may require or have extensive use of inputs and permissioned resources, and are controlled by their hosting application. When a running application is halted, the application closes its application-controlled augments but can choose to have the XR system run a “place-holder” world-controlled augment for as long as the application is not running. The place-holder world-controlled augment preserves the appearance of the application in the artificial reality environment but uses few system resources.

Abstract: Digital image processing methods performed by a computer are disclosed. In one example, a digital image captured by a real camera having intrinsic and extrinsic parameters is received. One or more distortion correction transformations are applied to the digital image to generate a distortion-corrected digital image. The distortion-corrected digital image is sub-divided into a plurality of distortion-corrected sub-images. For each distortion-corrected sub-image of the plurality of distortion-corrected sub-images, the distortion-corrected sub-image is associated with a synthesized recapture camera having synthesized intrinsic and extrinsic parameters mapped from the intrinsic and extrinsic parameters of the real camera.

Abstract: A device and system for visual reasoning in augmented reality environments employs adaptive multi-frame capture triggered by detection of user speech. Upon detecting speech, the device or system captures image frames at an initial frame capture rate, increasing capture frequency when a hand is detected in a captured image. Timestamped frames and transcribed speech form a prompt for a multimodal large language model, which extracts relevant details with constrained output. A separate language model then generates a final response. This two-stage approach optimizes processing efficiency and accuracy while preserving privacy by limiting continuous visual data collection. The system enables more natural and context-aware interactions in AR settings without complex gesture recognition algorithms.

Abstract: Three-dimensional (3D) images of a physical environment is obtained. The 3D images are modeled as a 3D data set with real-world objects depicted within the 3D data set. The objects are categorized into independent layers of the physical environment. Each layer is independently modified or enhanced to correct missing image information and image blemishes. The image data of 3D data set is updated with the corrected layers. The 3D data set and the independent layers are associated together as an extensible image data model. The extensible image data model is provided via interfaces to simulate object layout changes within the physical environment and to provide virtual reality (VR) and/or augmented reality (AR) shopping experiences through interfaces.

Abstract: Disclosed herein are systems, methods, and computer program products for object detection. The methods comprise performing the following operations by a computing device: obtaining an image that comprises a plurality of layers superimposed on each other; identifying a center point of a robot on a map; selecting a portion of the map contained in a geometric shape overlaid on the map so as to have a center set to the center point of the robot; obtaining map information associated with the selected portion of the map; generating at least one additional layer using the map information; superimposing the at least one additional layer onto the image to generate a modified image; and performing an object detection algorithm to detect at least one object in the modified image.

Abstract: An image display method, a device, and a medium. The image display method includes acquiring a real-time image of a target body part; and displaying a composite image in real time. The composite image is an image obtained by superposing a target three-dimensional image onto the target body part in the real-time image, the target three-dimensional image is obtained by rendering a wearable component three-dimensional model based on a real-time posture and a real-time unoccluded area of the target body part, and the real-time posture and the real-time unoccluded area are determined based on the real-time image.

Abstract: A communication management server includes circuitry to receive, from a mobile device being movable in a real space and a first communication terminal, information indicating positions of the mobile device and the first communication terminal in the real space. The circuitry generates a virtual space image including an icon of the mobile device and an icon of the first communication terminal that are associated with corresponding positions in a virtual space to appear on the virtual space image based on the information received, and including an icon of a second communication terminal. The circuitry transmits the virtual space image to the second communication terminal and establishes voice communication between the first communication terminal and the second communication terminal in response to receiving, via the second communication terminal, an operation of associating the icon of the second communication terminal with the icon of the mobile device on the virtual space image.

Abstract: Generating an overview image of an object includes, during a first capture duration, scanning regions of the object along a trajectory with illumination radiation, where the trajectory is chosen individually on the basis of properties of the object. First images of the object which together with position data (x, y, z) of an absolute distance measurement system are stored as an individual overview image are captured during the scanning of the trajectory. During a second capture duration, at least regions of the object are scanned with illumination radiation, and second images are captured; regions of the object which have already been imaged during the first capture duration are not imaged again. The first images captured during the first capture duration and the second images captured during the second capture duration are merged to form a resultant overview image of the object.

Abstract: In various implementations, methods of presenting an audio/SR experience are disclosed. In one embodiment, while playing an audio file in an environment, in response to determining that the respective temporal criterion and the respective environmental criterion of an SR content event is met, the SR content event is displayed in association with the environment. In one embodiment, SR content is obtained and displayed in association with an environment based on an audio file and a 3D point cloud of the environment. In one embodiment, SR content is obtained and displayed in association with an environment based on spoken words of a real sound of the environment.

Abstract: The disclosure provides a three-dimensional CT imaging method and apparatus. The method includes: collecting two DR images with a perpendicular relationship for an object to be imaged; inputting the two DR images into a preset three-dimensional volume reconstruction model to obtain a three-dimensional volume of the object outputted by the three-dimensional volume reconstruction model; and slicing the three-dimensional volume to obtain three-dimensional CT imaging of the object, wherein the preset three-dimensional volume reconstruction model is trained using multiple training samples, each training sample comprising: a DR image group composed of two DR images with a perpendicular relationship, a pseudo-sinogram corresponding to the DR image group, and a three-dimensional volume corresponding to the DR image group.

Abstract: A computer implement method includes obtaining a previously captured virtual tour data of a location, receiving real-time image data of a target object located within a field of view area of a camera, which target object is located in the same location wherein the virtual tour data was captured, analysing the real-time image data for detecting a deviation, and overlaying the real-time image data on an area of a virtual tour view for forming a mixed image virtual tour data, which area of the virtual tour view corresponds the field of view area, if the deviation is detected.

Abstract: A method including receiving a data structure including a model including a virtual object. The virtual object has spatial elements that form an area of the virtual object. The method also includes applying a ray tracing algorithm to the model. The ray tracing algorithm directs virtual rays from a remote point in the model towards the virtual object. The method also includes determining intersection values. Each of the intersection values represents a corresponding number of times that the virtual rays intersect a corresponding one of the spatial elements. The method also includes generating, from the intersection values, a coverage value representing a percentage of the area that is covered by the virtual rays. The method also includes returning the coverage value.

Abstract: Methods and processors for rendering a 3D object are disclosed. The method includes acquiring multi-camera image input including first image frames of the 3D object generated by a first camera and second image frames of the 3D object generated by a second camera, acquiring an initial 3D Gaussian Splatting (3DGS) model having a plurality of initial parameters including an initial frame-wise GS parameter and an initial camera-wise GS parameter, generating an adjusted 3DGS model by adjusting, based on the multi-camera image input, at least one of: the initial frame-wise GS parameter, the initial camera-wise GS parameter, generating, by the adjusted 3DGS model, a 3DGS output and rendering a 2D image of the 3D object using the 3DGS output.

Abstract: The present disclosure relates to a video generation method and apparatus, a device, and a storage medium. After acquiring one or more images to be processed, a plurality of target images having different degrees of eye opening are generated according to the images to be processed, and a video having a process of gradual eye change is generated on the basis of the plurality of target images.

Abstract: Techniques and systems are provided for generating a three-dimensional facial model. For instance, a process can include: obtaining a frame, the frame including a face; obtaining a mesh 3D model of the face; generating facial texture information associated with the face based on the frame and the mesh 3D model; generating, based on the facial texture information, displacement map information; and applying the displacement map information to the mesh 3D model to generate a finetuned mesh 3D model.

Abstract: A design device for designing a print includes a design section configured to design the print according to an instruction of a user, a three-dimensional display section configured to cause a three-dimensional preview of the designed print to be displayed, and an unrolled display section configured to cause an unrolled preview of the designed print to be displayed. Both the three-dimensional preview and the unrolled preview are simultaneously visibly displayed, and a result of a predetermined operation performed by a user on one of the three-dimensional preview and the unrolled preview is reflected on both the three-dimensional preview and the unrolled preview.