Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating three-dimensional meshes representing two-dimensional images for editing the two-dimensional images. The disclosed system utilizes a first neural network to determine density values of pixels of a two-dimensional image based on estimated disparity. The disclosed system samples points in the two-dimensional image according to the density values and generates a tessellation based on the sampled points. The disclosed system utilizes a second neural network to estimate camera parameters and modify the three-dimensional mesh based on the estimated camera parameters of the pixels of the two-dimensional image. In one or more additional embodiments, the disclosed system generates a three-dimensional mesh to modify a two-dimensional image according to a displacement input.

Abstract: A method for improving graphics performance is provided. The method includes: determining whether a current frame rendered into a frame buffer is a first frame in a first vertical synchronization (VSYNC) period defined by a first VSYNC signal; and pre-rendering a first next frame into the frame buffer in the first VSYNC period when the current frame is the first frame, wherein the first next frame is a frame that is next to the first frame.

Abstract: Methods and systems are disclosed for performing operations comprising: receiving an image that includes a depiction of a person wearing a fashion item; generating a segmentation of the fashion item worn by the person depicted in the image; identifying a facial expression of the user depicted in the image; and in response to identifying the facial expression, applying one or more augmented reality elements to the fashion item worn by the person based on the segmentation of the fashion item worn by the person.

Abstract: Example systems, devices, media, and methods are described for controlling the presentation of one or more virtual or graphical elements on a display in response to bimanual hand gestures detected by an eyewear device that is capturing frames of video data with its camera system. An image processing system detects a first hand and defines a mapped region relative to a surface of the detected first hand. The system presents a virtual target icon at a position within or near the mapped region. The image processing system detects a series of bimanual hand shapes, including the detected first hand and at least one fingertip of a second hand. In response to determining whether the detected series of bimanual hand shapes matches a predefined hand gesture, the system executes a selecting action that includes presenting one or more graphical elements on the display.

Abstract: The present teaching relates to method, system, medium, and implementations for region boundary identification and overlay display. An input associated with a 3D object is received. A 3D volumetric model is obtained for the 3D object with multiple regions, each of which includes multiple labeled voxels. A mesh representation is generated for the surface of the 3D object. Region boundaries on surface of the 3D object are identified based on the 3D volumetric model and the mesh representation. The 3D object is rendered, and the region boundaries are overlaid on the rendered 3D object.

Abstract: There is provided an apparatus for generating a 3D object texture map. The apparatus may comprise: a memory; and a processor, wherein the processor is configured to: generate a partial texture image by mapping object information in an input image into a texture space; obtain a sampling image by inputting the partial texture image to a sampler network trained according to a curriculum for selecting at least one of a training partial texture image, an aligned partial image in which the training partial texture image is aligned in the texture space, or an augmented partial image augmented from the aligned partial image; obtain a blending mask and a refined image by inputting the sampling image to a refiner network; and generate a 3D object texture map by blending the sampling image and the refined image based on the blending mask.

Abstract: Provided is a method of establishing a remote multiparticipant augmented reality session such that participants in the remote multiparticipant augmented reality session are at different locations and are in different physical environments. Augmented reality objects may be populated in a shared virtual space that has components of both physical environments and some of those augmented reality objects are controlled by the remote participant by exchanging participant state information.

Abstract: Disclosed herein is an environmental scanning tool that generates a digital model representing the surroundings of a user of an extended reality head-mounted display device. The environment is imaged in both a depth map and in visible light for some select objects of interest. The selected objects exist within the digital model at higher fidelity and resolution than the remaining portions of the model in order to manage the storage size of the digital model. In some cases, the objects of interest are selected, or their higher fidelity scans are directed, by a remote user. The digital model further includes time stamped updates of the environment such that users can view a state of the environment according to various timestamps.

Abstract: Various methods and systems are provided for image data segmentation. In one example, a method includes receiving a first segmentation input selecting a first set of pixels of a two-dimensional (2D) projected rendering, the 2D projected rendering generated from a 3D medical image dataset, retropropagating the selected first set of pixels to 3D space based on a mapping between the 2D projected rendering and the 3D medical image dataset to form a 3D segmentation mask, and saving the 3D segmentation mask in memory and/or applying the 3D segmentation mask to the 3D medical image dataset, wherein the 2D projected rendering is an intensity projection rendering.

Abstract: A scan conversion apparatus using a graphics processing unit (GPU) is proposed. The scan conversion apparatus may include an input unit that receives an input of N-th azimuth information (N is a natural number) of a radar, and a controller. The controller may check the sampling number of the inputted N-th azimuth information, and compare the checked sampling number of the N-th azimuth information with the sampling number of a preset scan conversion to determine whether to perform additional sampling. The controller may also perform additional sampling through a GPU according to a determined result, and generate a texture map by using the N-th azimuth information which is additionally sampled or not additionally sampled. The controller may further draw an N-th triangular shape on the basis of the center coordinates of a circle through the GPU, and then perform a scan conversion on the texture map by texture mapping.

Abstract: An augmented reality (AR) device and a method of predicting a pose in the AR device is provided. In the augmented reality (AR) device inertial measurement unit (IMU) values corresponding to the movement of the AR device are obtained at an IMU rate, intermediate 6-degrees of freedom (6D) poses of the AR device are estimated based on the IMU values and images around the AR device via a visual-inertial simultaneous localization and mapping (VI-SLAM) module, and a pose prediction model for predicting relative 6D poses of the AR device is generated by performing learning by using a deep neural network.

Abstract: A system is provided for generating and displaying a sequence of three-dimensional (3D) graphics that illustrate motion of the heart over a cardiac cycle. The system generates a start heart wall mesh and an end heart wall mesh that represent a start geometry and an end geometry of a heart wall derived from a start 3D image and an end 3D image. The system then generates one or more an intermediate heart wall 3D meshes based on an intermediate geometry of the heart wall. An intermediate geometry is interpolated based on the start geometry and the end geometry factoring a start time of a start heart wall mesh, an end time of the end heart wall mesh, and an intermediate time for the intermediate heart wall mesh. The system then displays in sequence representations the heart wall 3D meshes to illustrate the motion.

Abstract: Concurrently with performing a visibility pass to generate visibility data for two or more bins of an image, a processing system determines whether a primitive to be rendered covers at least a predetermined threshold percentage of a tile of the image. In response to the primitive coving at least the predetermined threshold percentage of the tile, the processing system stores the depth data of the primitive in a depth buffer for pixel-based rendering. In response to the primitive not covering at least the predetermined threshold percentage of the tile, the processing system fuses the primitive with one or more preceding primitives sharing an edge with the primitive in the tile to generate a fused primitive. In response to the fused primitive being valid in the tile, the processing system passes the depth data of the fused primitive to the depth buffer.

Abstract: Systems and methods for providing visual indications of generative model responses can include obtaining a user input and processing the user input with a generative model to generate a model-generated-response. The systems and methods can process the model-generated response and an image of an environment to generate an augmented image. The augmented image can include visual indicators of the model-generated response, which can include annotating the image based on detected features within the image. Generation of the augmented image can include object detection and annotation based on the content of the model-generated response.

Abstract: Apparatus and methods are provided for extracting and displaying information and data from a stream of information on a pair of smart glasses. One or more content filters describing the desired information and data may be communicated to a content filtering module. The content filtering module may process the stream of information to search for the desired information and data. When the desired information is found within the stream of information, the content filtering module may highlight the desired information, while blurring all other information, within a display on the pair of smart glasses.

Abstract: Provided is a data processing device for processing data acquired by an electrophoretic analysis. A graph creator (31, 33) creates an electropherogram and/or a separation image of peaks on an electrophoretic channel. A display processor (37) displays a graph showing the electropherogram and/or the separation image on which a boundary line is drawn to define the inside and the outside of an analysis target range extending along an axis of a separation direction, with the inside and the outside being shown in different visual modes. An analysis condition setter (34) receives an operation by a user for moving the boundary line on the graph displayed and sets the analysis target range whose position and size on the axis are changed according to the received operation. A data-analysis processor (35, 36) carries out a predetermined computation using all or some of peaks included in the analysis target range.

Abstract: A processing system including at least one processor may identify a user viewpoint of a user at a first venue, match a viewpoint at a second venue to the user viewpoint of the user at the first venue, detect a trigger condition to provide visual content of the second venue to the user at the first venue, obtain the visual content of the second venue, wherein the visual content of the second venue is obtained from the viewpoint at the second venue, and provide the visual content of the second venue to an augmented reality device of the user at the first venue, where the augmented reality device presents the visual content of the second venue as a visual overlay within a field of view of the user.

Abstract: Examples described herein relate to a display engine. In some examples, at least one processor is to generate one or more planes of a frame and store the generated one or more planes of a frame into the at least one memory. In some examples, the at least one processor is to determine whether a plane in the frame is a candidate plane for compression. In some examples, for the candidate plane for compression, based on the candidate plane not being subject to compression, the at least one processor is to adjust a plane level of the candidate plane to subject the candidate plane to compression. In some examples, the plane level of the candidate plane to subject the candidate plane to compression is a bottom most level. In some examples, for the candidate plane for compression, based on the candidate plane not being subject to compression and the candidate plane including content that would be occluded by an upper level plane, the at least one processor is to retain a plane level of the candidate plane.

Abstract: The present disclosure is directed toward systems and methods for retargeting a user's input digital design based on a selected template digital design. For example, in response to the user's selection of a template digital design, one or more embodiments described herein change various design features of the user's input digital design to match corresponding design features in the selected template digital design. One or more embodiments described herein also provide template digital designs to the user for use in retargeting after a two-step selection process that ensures the provided template digital designs are compatible with the user's input digital design.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for displaying augmented reality content. The program and method provide for receiving, from a first application running on a device, a request to switch to a second application on the device, the request identifying augmented reality content to display with image data captured by a camera of the device; providing, in response to receiving the request, for switching from the first application to the second application; providing for the second application to activate the camera to capture the image data; and providing for the second application to display the image data captured by the camera with the augmented reality content.