Abstract: A virtual staging platform includes a staging model. In some examples, the platform also includes a removal model, and/or a multi-view staging model. The staging model uses a diffusion model useable to generate a low-resolution staged image and a rendering module useable to improve and introduce photorealistic features into the staged image. The removal model is implemented using a diffusion model and uses a binary mask identifying areas including objects for removal. The multi-view staging model receives two images of a space taken from two different perspectives, and generates a three-dimensional reconstruction of the scene. A view from at least one of the images is staged, and the staged objects are made consistent across the two images.

Abstract: Various implementations disclosed herein include devices, systems, and methods that enable concurrent viewing of both virtual and real 3D environments. This may involve presenting a virtual environment overlaying a physical environment. For example, a process may align a 3D representation of a second environment with a 3D coordinate system of a physical environment and determining a viewpoint within the 3D coordinate system based on a position of the electronic device within the physical environment. The process may further include presenting a view of the physical environment with an overlaid view of the 3D representation of the second environment based on the viewpoint. The overlaid view of the 3D environment includes visible lines defining transparent portions through which at least a portion of the view of the physical environment is visible.

Abstract: Apparatuses, systems, and techniques for constructing a data structure to store a shape of an object based at least in part on a portion of multiple images, and obtaining poses of the object by tracking a pose of the object through the multiple images based at least in part on the data structure. Optionally, the poses may be used to generate a plan for a path of a device to travel, generate a rendering of at least a portion of a Mixed Reality (“MR”) display to be viewed by a user, and/or the like.

Abstract: Systems and methods are provided for generating, in real-time, recommendations for different data elements for different virtual three-dimensional environments. As users interact with data elements presented within these virtual three-dimensional environments, these interactions and changes are processed using a machine learning algorithm in real-time to provide recommendations for new data elements that can be introduced in these virtual three-dimensional environments. Based on responses to these recommendations, the new data elements can be introduced in these virtual three-dimensional environments. Further, the machine learning algorithm is dynamically updated based on these responses.

Abstract: A media application receives a set of images that include a source image and a target image, the source image and the target image including at least a subject. The media application determines whether to use one or more editors selected from a group of a head editor, a face editor, or combinations thereof. Responsive to determining to use the head editor, the media application generates a compositive image by replacing at least a portion of head pixels associated with a target head of the subject in the target image with head pixels from a source head of the subject in the source image and replacing neck pixels associated with a target neck and shoulder pixels associated with target shoulders that include an area between the target head and a target torso with an interpolated region that is generated from an interpolation of the source image and the target image.

Abstract: A method enabling head-tracking-based media selection for video communications implemented by a system is provided, comprising implementing a 3D virtual environment configured to be accessed by a plurality of client devices, each having a corresponding user graphical representation within the 3D virtual environment, each user graphical representation having a corresponding virtual camera; receiving head tracking metadata of a first client device that comprises 6 degrees of freedom head tracking information generated in response to tracking movement of key facial landmarks; identifying graphical elements within a field of view of the virtual camera of a second client device, wherein the identified graphical elements comprise the user graphical representation of the first user; and sending, to the second client device, the head tracking metadata and the identified graphical elements.

Abstract: A system for computer assisted navigation during surgery includes a computer platform that operates to register a target surgical area of a patient. In certain cases, a process includes: obtaining a pre-op CT image of a pelvic region of a patient and intra-operatively obtaining a point cloud data about the pelvic region with a navigated instrument, generating a 3D bone model which excludes non-targeted area such as a femur, and then merging the 3D bone model to the point cloud to register the target surgical area.

Abstract: In various examples, systems and methods are disclosed that relate to performing inter-accelerator data transfers. For example, an accelerator such as a pixel processing engine (PPE) can include multiple processing engines (PEs). The PEs can be arranged in a two-dimensional array and each PE can be configured to receive data in the registers of the PEs. The PEs can transfer data between registers of the same or different PEs. The PEs can also be configured to perform transfers and operations in sequence to perform complex functions such as filtering.

Abstract: In a method for updating a game map, an update interval of a first map element to be displayed in the game map is determined based on a change frequency of the first map element. The first map element is displayed in the game map. The display of the first map element in the game map is updated based on the determined update interval of the first map element. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

Abstract: Disclosed are a method of displaying an image (for example, wallpaper) on a display and an electronic device supporting the same. The electronic device may include a display, a memory, and at least one processor comprising processing circuitry. At least one processor, individually and/or collectively, may be configured to: separate a main object from a background object in an image; determine a display size of a display to display an edited image; edit (modify) each of the main object and the background object based on the display size; combine the edited main object and the edited background object and generate the edited image based on the display size; and display the edited image through the display.

Abstract: Disclosed are free-form curved surface slicing method and device based on implicit model, includes following: (1) Using mesh model of layered curved surface to intersect with implicit model of a part to be manufactured to obtain contour lines; (2) Comparing rules for intersecting contour lines and meshes within mesh, mesh coordinates are substituted into implicit model, obtaining a position of an intersection point of contour lines in corresponding mesh; (3) Using interpolation method to calculate intersection coordinates of contour lines and mesh boundary, specifying storing sequence of interpolation points, storing intersection points of discrete line segments in mesh; (4) Merging unordered point sets obtained to establish topological relationship between point sets and discrete line segments, each line segment corresponds to two endpoints, each endpoint corresponds to two line segments, based on above, all points traversed will be connected into complete and ordered profile, that is sliced profile.

Abstract: Disclosed is a motion generation device for generating motion based on input information including a text and an operation method thereof, and the motion generation device may include a memory configured to store at least one instruction; and at least one processor configured to execute the at least one instruction stored in the memory, wherein the at least one processor is configured to: obtain the input information including the text representing a movement of a character, extract feature information from the obtained input information, generate motion data for the movement of the character using the extracted feature information, obtain correction motion data by post-processing the generated motion data, and generate motion animation of the character based on the obtained correction motion data.

Abstract: Disclosed herein are a video fusion method, apparatus, electronic device and storage medium. The video fusion method comprises: receiving a foreground video frame to be fused in a foreground video stream to be fused and a background video frame to be fused in a background video stream to be fused; determining a fusion parameter corresponding to the background video frame to be fused; according to a target foreground processing method corresponding to the foreground video frame to be fused and the fusion parameter, determining a target object to be fused corresponding to the foreground video frame to be fused; according to the target object to be fused and the background video frame to be fused, determining the target fused video frame to be displayed at a target terminal.

Abstract: The invention provides, in some aspects, a system for rendering images, the system having one or more client digital data processors and a server digital data processor in communications coupling with the one or more client digital data processors, the server digital data processor having one or more graphics processing units. The system additionally comprises a render server module executing on the server digital data processor and in communications coupling with the graphics processing units, where the render server module issues a command in response to a request from a first client digital data processor.

Abstract: An information processing apparatus according to the present invention includes a processor, and a memory storing a program which, when executed by the processor, causes the information processing apparatus to acquire information regarding a personal space of a second user displayed in a three-dimensional space viewed by a first user, acquire information regarding a distance from the first user to a display position of the second user in the three-dimensional space, and determine whether to display the second user at the display position so that the first user does not enter the personal space, on a basis of the personal space and the distance.

Abstract: A handheld controller for an artificial-reality system may include a top cover having a surface surrounded by a perimeter. The surface has a digit-occluded region on which a digit of a user of the handheld controller can be placed and a different region separated from the digit-occluded region. A first illumination source is disposed within the digit-occluded region at a first position along the perimeter of the top cover. The first position is visible to a camera of the artificial-reality system while the handheld controller has one of a first set of orientations. A second illumination source is disposed within the digit-occluded region at a second position along the perimeter of the top cover while the handheld controller has one of a second set of orientations. A third illumination source is disposed within the different region at a third position away and distinct from the perimeter on the surface.

Abstract: According to systems and techniques disclosed herein, a method for generating a navigable three-dimensional image of a tissue sample may include receiving a plurality of whole slide images (WSI) associated with the tissue sample. The method may further include providing the plurality of whole slide images to a machine-learning model. The machine-learning model may have been trained to identify one or more positional features within the plurality of whole slide images and output a plurality of relative positional relationships corresponding to each of the plurality of whole slide images. The method may further include generating the navigable three-dimensional image of the tissue sample based on the plurality of relative positional relationships. The method may further include generating an interactive display incorporating the navigable three-dimensional image. The method may further include providing, to a user interface, the interactive display.

Abstract: An image generation system and method for displaying an Augmented Reality “AR” image of a real-world environment having one of more objects located therein and one or more AR objects each corresponding to a respective object, the system comprising: a display on which the image of the real-world environment and the AR objects are displayed; a processing and control module configured to: receive, from one or more sensors, data relating to the real-world environment and objects therein; create the one or more AR objects from the objects by determining additional information relating to the object which is represented by at least one of symbols, annotations and fonts to be attached to the AR object to act as a displayed component: displaying the AR image comprising the real-world image and one or more AR objects; wherein the AR objects once created are stored for future retrieval based on a unique identifier for the AR object which remains active as long as the object is of interest.

Abstract: A device may include a processor configured to determine a first position of a physical camera in a physical environment, transmit the first position to a second device, obtain metadata of the physical camera, and cause a modification of a virtual camera of the second device based on the metadata. The processor is also configured to obtain, from the second device, at least one virtual image frame captured by the virtual camera placed at a second position in a computer-generated environment, and to obtain, from the physical camera, at least one image frame captured from the physical environment. The processor is also configured to generate a composite image frame including at least a portion of at least one virtual image frame composited with at least a portion of the at least one image frame, and display the composite image frame.

Abstract: Systems and methods are disclosed for generating edit captions based on layout representations. The system may access one or more reference layout representations associated with one or more reference images and a target layout representation associated with a target image. The system may compare the one or more reference layout representations with the target layout representation to determine semantic differences or correspondences. The system may identify one or more differences between the one or more reference images and the target image, the differences including modifications to objects, spatial relationships, or contextual features. The system may generate one or more edit captions based on the identified differences.