Abstract: Methods of removing text from digital video or still images are disclosed. An image processing system receives an input image set defining a region of interest (ROI) that contains text. The system determines an input background color for the ROI. The system applies a text infilling function to remove text from the ROI to yield a preliminary output image set. The system may determine a residual corrective signal that corresponds to a measurement of background color error between the input set and the preliminary output set. The system may apply the residual corrective signal to the ROI in the preliminary output set to yield a final output set that does not contain the text. Alternatively, the system may remove background from the ROI of the input set before text infilling, then return background to the ROI after the text infilling.

Abstract: A computer implemented method for warping virtual content from two sources includes a first source generating first virtual content based on a first pose. The method also includes a second source generating second virtual content based on a second pose. The method further includes a compositor processing the first and second virtual content in a single pass. Processing the first and second virtual content includes generating warped first virtual content by warping the first virtual content based on a third pose, generating warped second virtual content by warping the second virtual content based on the third pose, and generating output content by compositing the warped first and second virtual content.

Abstract: A system for personalizing augmented reality for individuals that is easy to use. There is a central server with instructions for selecting or creating a personally meaningful multimedia object. A sound wave and an image of the sound wave are generated from the object. A tattoo of the generated image is applied as a tattoo, either permanently or temporarily, to a person. Automatically generating, assigning and storing a unique identifier from an uploaded image of the tattoo, the generated image, and the multimedia object to the central server. Capturing an image of the tattoo on the person using a smart device, where the smart device has instructions to determine the unique identifier from an image captured by the smart device. Retrieving and downloading, aligning and overlaying the stored multimedia where it is played back.

Abstract: Efficiency of work for laying out an object extracted from an image on another image is improved, and a burden on a user who performs the work is reduced. In S6, a second image attribute information extraction unit 15 extracts attribute information of a second image. In S7, a layout determination unit 16 determines a combining position of the object in the second image based on object attribute information, object surrounding attribute information, and second image attribute information. In S8, a correction unit 17 corrects at least one of the extracted object or the second image based on the object attribute information, the object surrounding attribute information, and the second image attribute information. In S9, the combining unit 18 creates a composite image obtained by combining the object (corrected object in a case where correction on object is performed) at a combining position of the second image (corrected second image in a case where correction on second image is performed).

Abstract: A method and apparatus for recognizing face-swap, a device and a computer readable storage medium are provided, and relates to the field of computer technology. An implementation of the method includes: performing face detection on a to-be-recognized image to determine a face area in the to-be-recognized image; extending the face area to a head area in the to-be-recognized image, to generate an image of the head area; occluding at least one part of the face area in the image of the head area, to obtain an occlusion image; and determining, based on the occlusion image and a pre-trained face-swap recognition model, a face-swap recognition result of the to-be-recognized image, the face-swap recognition model being used to determine whether a face in the to-be-recognized image is swapped with a preset face.

Abstract: Methods and apparatus to transition between 2D and 3D renderings of augmented reality content are disclosed. An example apparatus includes at least one processor to execute instructions to: determine a first intended movement of an augmented reality (AR) object projected onto a first surface in a real world environment; cause the AR object to be rendered to appear to move along the first surface at a fixed depth defined by the first surface; determine a second intended movement of the AR object projected onto a second surface in the real world environment; and cause the AR object to be rendered to appear to move with variable depth within a 3D virtual space, the 3D virtual space defined by the second surface and a virtual rear boundary, the virtual rear boundary to virtually extend behind the second surface from a perspective of a user.

Abstract: Embodiments of present disclosure disclose method and system for generating a medical image based on a textual data in a medical report. For generation, a textual data from each of one or more medical reports of the patient is retrieved. The textual data comprises one or more medical events and corresponding one or more attributes associated with each of the one or more medical reports. Further, a matching score for each of plurality of reference images is computed based on the textual data, using a first machine learning model. Upon computing the matching score, one or more images are selected from the plurality of reference images based on the matching score associated with each of the plurality of reference images. The medical image for the patient is generated based on the one or more images and the textual data using a second machine learning model.

Abstract: A surgical navigation system includes: a 3D display system with a see-through visor; a tracking system comprising means for real-time tracking of: a surgeon's head, the see-through visor, a patient anatomy and a surgical instrument to provide current position and orientation data; a source of an operative plan, a patient anatomy data and a virtual surgical instrument model; a surgical navigation image generator configured to generate a surgical navigation image with a three-dimensional image representing simultaneously a virtual image of the surgical instrument corresponding to the current position and orientation of the surgical instrument and a virtual image of the surgical instrument indicating the suggested positions and orientation of the surgical instrument according to the operative plan data based on the current relative position and orientation of the surgeon's head, the see-through visor, the patient anatomy and the surgical instrument; wherein the 3D display system is configured to show the surgica

Abstract: A projector includes a projection section that projects a first image on a projection surface, a control section that causes the projection section to project a pattern image for installation including a first pattern that is located at an end of the first image, which overlaps with a second image, and a second pattern that is so disposed that a first straight line section is located in a position separate from the end by a distance, and a correction section that corrects the first image based on a captured image containing an image of a first area of the second image, and the first area is an area that overlaps with an area having a width corresponding to the distance measured from the end of the first image in a state in which the first image and the second image overlap with each other.

Abstract: Systems and methods for container access to graphics processing unit (GPU) resources are disclosed herein. In some embodiments, a computing system may include a physical GPU and kernel-mode driver circuitry, to communicatively couple with the physical GPU to create a plurality of emulated GPUs and a corresponding plurality of device nodes. Each device node may be associated with a single corresponding user-side container to enable communication between the user-side container and the corresponding emulated GPU. Other embodiments may be disclosed and/or claimed.

Abstract: Embodiments are provided for digital dental modeling. One method embodiment includes receiving a three-dimensional data set including a first jaw and a second jaw of a three-dimensional digital dental model and receiving a two-dimensional data set corresponding to at least a portion of the first jaw and the second jaw. The method includes mapping two-dimensional data of the two-dimensional data set to the three-dimensional digital dental model by transforming a coordinate system of the two-dimensional data to a coordinate system of the three-dimensional data set. The method includes positioning the first jaw with respect to the second jaw based on the two-dimensional data mapped to the three-dimensional data set. The method includes using at least a portion of the two-dimensional data mapped to the three-dimensional data set as a target of movement of the first jaw with respect to the second jaw in the three-dimensional digital dental model.

Abstract: An augmented reality (AR) platform supports concurrent operation of multiple AR applications developed by third-party software developers. The AR platform may include an application programming interface (API) that third-party software developers can use to integrate features of the AR platform into the overall user experience of their AR applications. The AR platform includes a feature set having a variety of AR-specific features that interact with and are accessible to the AR applications or AR layers that define a collection of AR content.

Abstract: An apparatus to facilitate cache replacement is disclosed. The apparatus includes a cache memory and cache replacement logic to manage data in the cache memory. The cache replacement logic includes tracking logic to track addresses accessed at the cache memory and replacement control logic to monitor the tracking logic and apply a replacement policy based on information received from the tracking logic.

Abstract: A system, method and computer program product are provided for generating line-of-sight information using imagery. In some aspects, the method includes receiving a raster image depicting at least one object in a region of interest, and measuring a shadow of the at least one object in the raster image. The method also includes determining an angle of the sun from the shadow of the at least one object, and creating a plurality of virtual shadows for the at least one object using the angle of the sun. The method further includes generating line-of-sight information for the at least one object based on an intersection of the plurality of virtual shadows with objects in the region of interest.

Abstract: The disclosure discloses a method for processing map data, a device, and a storage medium. The detailed implementing solution includes: determining POI data of bound points of interest (POI) of a road to be marked in response to obtaining a road marking instruction; selecting target POI data from the POI data of the bound POIs based on a scene where a user is located; and rendering a map interface based on road information of the road to be marked and the target POI data, and displaying the map interface rendered.

Abstract: Systems and methods for segmenting scan data are disclosed. The methods include receiving scan data representing a plurality of points in an environment associated with a ground surface and one or more objects, and creating a graph from the scan data. The graph includes a plurality of vertices corresponding to the plurality of points. The method further includes assigning a unary potential to each of the plurality of vertices that is a cost of assigning that vertex to a ground label or a non-ground label, and assigning a pairwise potential to each pair of neighboring vertices in the graph that is the cost of assigning different labels to neighboring vertices. The methods include using the unary potentials and the pairwise potentials to identify labels for each of the plurality of points, and segmenting the scan data to identify points associated with the ground based on the identified labels.

Abstract: A method for calibrating a wearable device includes displaying an image with a plurality of pixels for each of three primary colors using the wearable device, and determining RGB and XYZ values for each of the plurality of pixels. The method includes selecting a subset of the plurality of pixels to form a group of grid points, and dividing the image into a group of tile regions, with each tile region including a grid point. Grid XYZ values are determined for each grid point, based on averaging XYZ values of all pixels in a corresponding tile region, and a grid RGB-to-XYZ conversion matrix is determined for each grid point. The method also includes determining a correction matrix for each grid point by multiplying an inverse of the grid RGB-to-XYZ conversion matrix for the grid with an sRGB-to-XYZ conversion matrix.

Abstract: A visualization combination engine may be used to combine a first data visualization based on a first data set with a second data visualization based on a second data set. The combination process may be initiated by, for example, clicking and dragging the first data visualization onto the second data visualization. The visualization combination engine may create the combined data visualization without requiring the user to manually combine the first and second data sets. The combination may be carried out by identifying a key that is common between the two data sets and combining the first and second data sets into a combined data set based on the key, and then creating the combined data visualization based on the combined data set. One or more cues may be used during the process to provide helpful information and/or allow user selection of the properties of the combined data visualization.

Abstract: Techniques are disclosed relating to context switching in a SIMD processor. In some embodiments, an apparatus includes pipeline circuitry configured to execute graphics instructions included in threads of a group of single-instruction multiple-data (SIMD) threads in a thread group. In some embodiments, context switch circuitry is configured to atomically: save, for the SIMD group, a program counter and information that indicates whether threads in the SIMD group are active using one or more context switch registers, set all threads to an active state for the SIMD group, and branch to handler code for the SIMD group. In some embodiments, the pipeline circuitry is configured to execute the handler code to save context information for the SIMD group and subsequently execute threads of another thread group. Disclosed techniques may allow instruction-level context switching even when some SIMD threads are non-active.

Abstract: A method, a system, a device, and a computer readable storage medium for video reconstruction are disclosed. The method includes: obtaining an image combination of multi-angle free-perspective video frames, parameter data corresponding to the image combinations of the video frames, and position information of a virtual viewpoint based on a user interaction; selecting texture images and depth maps of corresponding groups in the image combinations of the video frames at a time moment of the user interaction according to a preset rule and based on the position information of the virtual viewpoint and the parameter data corresponding to the image combinations of the video frames; and combining and rendering the texture images and the depth maps of the corresponding groups based on the position information of the virtual viewpoint and parameter data corresponding to the depth maps and the texture images of the corresponding groups to obtain a reconstructed image.