Abstract: In examples, the number of rays used to sample lighting conditions of a light source in a virtual environment with respect to particular locations in the virtual environment may be adapted to scene conditions. An additional ray(s) may be used for locations that tend to be associated with visual artifacts in rendered images. A determination may be made on whether to cast an additional ray(s) to a light source for a location and/or a quantity of rays to cast. To make the determination variables such as visibilities and/or hit distances of ray-traced samples of the light source may be analyzed for related locations in the virtual environment, such as those in a region around the location (e.g., within an N-by-N kernel centered at the location). Factors may include variability in visibilities and/or hit distances, differences between visibilities and/or hit distances relative to the location, and magnitudes of hit distances.

Abstract: A method for determining experience quality of virtual reality (VR) multimedia includes, in a process of playing VR multimedia, obtaining a first sensory parameter, a second sensory parameter, and a third sensory parameter of the VR multimedia, where the first sensory parameter, the second sensory parameter, and the third sensory parameter are obtained by performing sampling separately according to at least two same perceptual dimensions, and are respectively parameters that affect fidelity experience, enjoyment experience, and interaction experience, and determining a mean opinion score (MOS) of the VR multimedia based on the first sensory parameter, the second sensory parameter, and the third sensory parameter of the VR multimedia. Because the third sensory parameter is a parameter that affects the interaction experience, an interaction feature of the VR multimedia is considered.

Abstract: Machine learning vision systems rely on very large numbers of training images to learn to recognize particular shapes and configurations of shapes. Traditionally, such datasets of training images needed to be selected and tagged (or labelled) manually. To recognize a particular object, such as a dog or vehicle, under realistic settings with an acceptable degree of reliability, may require data sets of thousands of images per object class. To improve this, a method is provided to generate datasets with a multiplicity of corresponding images are generated using a 3D rendering engine using a plurality of lighting arrangements and a plurality of views. Artefacts may also be introduced. In this way, very large data sets become feasible, with a variable degree of correspondence in each data set.

Abstract: Systems, methods, devices, and non-transitory media of the various embodiments enable for updating a point cloud, such as a two-and-a-half-dimensional (2.5D) point cloud. Various embodiments include receiving two point clouds, such as a base point cloud of a terrain area and a new point cloud of the terrain area, and fusing the received two point clouds to generate an up-to-date point cloud, such as an up-to-date point cloud model of the terrain. Various embodiments may be especially useful in generating models of terrain areas, such as construction sites, earthwork projects, shorelines, etc., surveyed by surveying technologies, such as drone-based aerial photogrammetry systems, Light Detection and Ranging (LiDAR) systems, etc.

Abstract: A method for graphics processing. The method including rendering graphics for an application using graphics processing units (GPUs). The method including using the plurality of GPUs in collaboration to render an image frame including a plurality of pieces of geometry. The method including during the rendering of the image frame, subdividing one or more of the plurality of pieces of geometry into smaller pieces, and dividing the responsibility for rendering these smaller portions of geometry among the plurality of GPUs, wherein each of the smaller portions of geometry is processed by a corresponding GPU. The method including for those pieces of geometry that are not subdivided, dividing the responsibility for rendering the pieces of geometry among the plurality of GPUs, wherein each of these pieces of geometry is processed by a corresponding GPU.

Abstract: Distance measurements are received from one or more distance measurement sensors, which may be coupled to a vehicle. A three-dimensional (3D) point cloud are generated based on the distance measurements. In some cases, 3D point clouds corresponding to distance measurements from different distance measurement sensors may be combined into one 3D point cloud. A voxelized model is generated based on the 3D point cloud. An object may be detected within the voxelized model, and in some cases may be classified by object type. If the distance measurement sensors are coupled to a vehicle, the vehicle may avoid the detected object.

Abstract: A data-driven, object-oriented, and customizable method for visualizing a three-dimensional (3D) structure is disclosed which includes receiving a model-based data file including instantiation of elements of a structure, identifying one or more instances of one or more objects, providing data associated with the plurality of polygons for the object geometry to a visualization engine, providing data associated with the plurality of polygons for the object placement information to the visualization engine, providing data associated with the plurality of polygons for the object color and transparency information to the visualization engine, providing data associated with the plurality of polygons for the object functional information to the visualization engine, generating a 3D model of the object based on the plurality of polygons, and outputting a rendering of the 3D model for displaying on a digital display.

Abstract: In a computing environment comprising a plurality of equipment racks wherein each equipment rack comprises one or more of compute, storage and network assets, the method captures an image of at least one equipment rack in the computing environment. The method identifies a known object in the image to determine physical characteristics of the equipment rack. The method receives, from a peer-to-peer network, positioning beacon signals respectively associated with at least a portion of the compute, storage and network assets in and around the equipment rack. The method determines a closest asset among the portion of the compute, storage and network assets for which positioning beacon signals are received. The method obtains data indicative of physical characteristics associated with the closest asset, obtains a model of the computing environment based on the obtained data, and then obtains a three-dimensional map of the computing environment based on the model.

Abstract: An image display method includes displaying an integrated video in which videos of a scene from different viewpoints are arranged in a frame, the videos including at least one real video and at least one virtual video generated from the at least one real video. A first user interface into which a first operation is input is displayed. Viewpoints of the displayed videos are changed according to the first operation. A second user interface into which a second operation is input is displayed. A playing speed of the displayed videos is changed according to the second operation.

Abstract: A method is provided, comprising: preventing rendering of specific audio in a virtual space to a user through virtual reality; enabling the user to explore the virtual space through user-perspective controlled virtual reality without hearing the specific audio; and in response to an interrupt, performing a visual transition to audio-visual content comprising the specific audio and visual content associated with the specific audio and then rendering specific audio and the visual content associated with the specific audio in the virtual space to the user through virtual reality.

Abstract: Methods, systems and computer program products for the generation of 3D images may include receiving a plurality of points that correspond to a surface of an object, generating a first mesh representation of a shape of the object, the first mesh representation comprising a plurality of polygons, respective ones of the plurality of polygons comprising at least three vertices and at least three edges, associating the plurality of points with a first set of the plurality of polygons, classifying a portion of the plurality of points as background points, and adjusting the first mesh representation of the object to create a second mesh representation of the object by removing from the first mesh representation at least one of the first set of the plurality of polygons that is associated with the portion of the plurality of points that are classified as the background points.

Abstract: This application discloses a method for determining a posture of a virtual object in a virtual environment performed at an electronic device. The method includes: determining at least one sampling point of the virtual object; determining a normal direction of the virtual object relative to the ground according to the at least one sampling point and the ground on which the virtual object is located; determining a ground-hugging posture of the virtual object in the virtual environment according to the normal direction; and rendering the virtual object in the virtual environment according to the ground-hugging posture. The normal direction of the ground on which the virtual object is located is determined according to the sampling point, and the ground-hugging posture of the virtual object in the virtual environment is obtained according to the normal direction.

Abstract: A method of rendering at least one of paths forming an object includes setting an initial value to each of tiles included in a frame based on a position and a proceeding direction of the at least one of paths, calculating a winding number of each of the tiles through which the at least one of paths passes, among the tiles included in the frame, based on the set initial value, and determining whether to perform shading based on the set initial value and the calculated winding number.

Abstract: Systems, methods, and devices are disclosed for applying concealment of components of an electronic device. In one embodiment, an electronic device may include a component that is disposed behind a display (e.g., a transparent organic light-emitting diode (OLED) display) that is configured to selectively become transparent at certain transparency regions. Additionally, the electronic device includes data processing circuitry configured to determine when an event requesting that the component be exposed occurs. The data processing circuitry may control portions of the display to become transparent, to expose the component upon the occurrence of the event requesting that the component be exposed.

Abstract: An image processing apparatus 200 includes: a first saturation information obtaining unit 306 configured to obtain saturation of a frame image; a second saturation information obtaining unit 309 configured to obtain saturation of a background image; and a threshold value determining unit 311 configured to determine a threshold value, which is used for checking a difference in color information, for each pixel, based on the saturation obtained by each of the first saturation information obtaining unit 306 and the second saturation information obtaining unit 309. A hue foreground area estimating unit 312 is configured to estimate a foreground area by use of the threshold value determined by the threshold value determining unit 311 as well as color information of the frame image and color information of the background image.

Abstract: Systems and methods are disclosed for directed image capture of a subject of interest, such as a home. Directed image capture can produce higher quality images such as more centrally located within a display and/or viewfinder of an image capture device, higher quality images have greater value for subsequent uses of captured images such as for information extraction or model reconstruction. Graphical guide(s) facilitate content placement for certain positions and quality assessments for the content of interest can be calculated such as for pixel distance of the content of interest to a centroid of the display or viewfinder, or the effect of obscuring objects. Quality assessments can further include instructions for improving the quality of the image capture for the content of interest.

Abstract: An XR device for providing an augmented reality (AR) mode and a virtual reality (VR) mode and a method for controlling the same are disclosed. The XR device is applicable to 5G communication technology, robot technology, autonomous driving technology, and Artificial Intelligence (AI) technology. When a sensor unit senses presence of a user who wears the XR device, the XR device captures a first image corresponding to a peripheral region of the display device by a camera, and controls the sensor unit to sense the peripheral region of the display device. The XR device creates a virtual 3D image corresponding to the peripheral region based on the first image and the sensed result, and controls a display to display the created virtual 3D image in another region that is different in position from a first screen image displayed on the display device.

Abstract: A method of producing a full resolution frame, comprising generating a tile representation of the frame. The tile representation comprises a plurality of tiles each associated with an area of the frame. The method also includes eliminating one or more predetermined portions of each tile and rendering retained portions of each tile to produce rendered tiles. The method also transforms the rendered tiles into processed tiles. The full resolution frame is then constructed from the processed tiles.

Abstract: A rendering process and system that may be used to composite virtual objects in panoramic video to provide a virtual reality and augmented reality experience. The process includes receiving low dynamic range (LDR) video data, e.g. 360° video; generating radiance maps, such as diffuse and specular maps, from the LDR data; inverse tone mapping the LDR data of the maps to generate high dynamic range (HDR) data for the maps; and receiving at least one virtual object and applying image based lighting (IBL) to the virtual object using the HDR data of the maps. A perceptually based threshold is also applied to radiance maps to detect prominent pixels, and using the prominent pixels as salient lights for image based shadowing (IBS) associated the virtual object. Objects are composited 360° video in real time using IBL and IBS without precomputation allowing user interaction with the objects.

Abstract: A synthetic image generation apparatus has a digital surface model (DSM) generator, a slope map generator, a curvature map generator and a synthetic image generator. The digital surface model (DSM) generator meshes three-dimensional point group data and generates a DSM including height of a building and vegetation. The slope map generator calculates a slope amount in accordance with the DSM and generates a slope map expressing levels of the slope amounts with shading in two colors. The curvature map generator smooths the DSM, calculates curvature in accordance with the smoothed DSM, and generates a curvature map expressing bumps and dips according to the curvature with shading in two colors. The synthetic image generator generates a synthetic image obtained by superimposing the slope map transmitted at first transmittance, the curvature map transmitted at second transmittance, and an orthochromatic image.