Abstract: Provided is a guide display device that prevents misidentification of the same feature as a plurality of different features or the ground surface even if an occlusion area occurs. A guide display device for a crane includes: a laser scanner that scans a suspended load and a ground surface from above the suspended load; and a data processing unit that calculates a representative point for each grid using the point cloud data acquired by the laser scanner, creates a three-dimensional map based on the representative points, and updates the three-dimensional map if the newly calculated representative point differs from the existing representative point. When an occlusion area, which is a shadow of the suspended load, occurs in the three-dimensional map, the occlusion area is not updated even if the newly calculated representative point and the existing representative point are different.

Abstract: Some embodiments include a method comprising using a first computing device to perform: obtaining an image of a scene captured using a camera coupled to the first computing device; obtaining camera setting values used to capture the image; determining, using the image, surface attribute values characterizing at least one surface shown in the image of the scene; generating an augmented reality (AR) interface at least in part by using the camera setting values and the surface attribute values to create a first composite image by overlaying a selected virtual furniture object onto the image so that the virtual furniture object is displayed in the AR interface as being on a first surface of the at least one surface shown in the image; and transmitting, to a second computing device and via at least one communication network, the first composite image, the camera setting values and the surface attribute values.

Abstract: Aspects presented herein relate to methods and devices for graphics processing including an apparatus, e.g., a GPU or a CPU. The apparatus may obtain visibility information for a set of primitives in at least one frame associated with the graphics processing, where the at least one frame includes a plurality of bins, such that at least one bin of the plurality of bins includes at least one primitive of the set of primitives. The apparatus may also configure a density map based on the visibility information for the set of primitives, where the density map includes density data associated with an amount of the set of primitives in each of the plurality of bins. Further, the apparatus may map the density data for each of the plurality of bins to a shading rate for each of the plurality of bins.

Abstract: Systems and techniques are provided for determining bounding regions for a hierarchical structure for ray tracing. For instance, a process can include obtaining an acceleration data structure, the acceleration data structure including one or more primitives of a scene object. A graph cut can be applied to the acceleration data structure. A set of nodes of the acceleration data structure can be determined based on the graph cut, wherein the determined set of nodes is located adjacent to the graph cut. A world-space bounding box can be generated for the scene object, using the set of nodes determined based on the graph cut.

Abstract: Various example embodiments provide a computing device of an algorithm for reconstructing a three-dimensional (3D) image in consideration of multiple scattering and a method of the same. According to various example embodiments, the computing device may be configured to set a 3D refractive index based on a plurality of 2D images for a specimen and to reconstruct a 3D image for the specimen from the set refractive index using a modified Born expansion considering multiple scattering to converge a calculation result.

Abstract: The embodiments of the present disclosure disclose subsurface scattering calculation method for translucent material rendering, which relates to the clipping and polynomial fitting of brute-force Monte Carlo photon tracking experimental results to accurately represent the energy attenuation of subsurface scattering in distance. On this basis, an average free path and a single scattering rate are used to determine the relationship of each term in the multinomial fitting formula so as to facilitate the calculation and adjustment of the reflection profile. In the end, through a new real-time importance sampling solution, the outgoing radiation from any point on the object surface is calculated by the Monte Carlo method. This importance sampling solution is also applicable to any other subsurface scattering calculation model. By combining this subsurface scattering calculation result with other results, such as highlight reflection, any translucent material object can be rendered accurately and efficiently.

Abstract: A system compresses and decompresses attribute information for visual volumetric content, such as a mesh representation. Attribute values are included in the visual volumetric representation, wherein at least some of the attribute values include unitary vectors, such as surface normal vectors or surface tangent vectors having a magnitude of one unit. In order to compress the attribute information the three-dimensional unit vectors are mapped into two dimensional parametric coordinates for a planar representation of a unit sphere. To reduce negative effects on compression due to distortion or discontinuities in the planar representation, mappings for compressing respective unit vectors are adaptively selected.

Abstract: Techniques are disclosed relating to intersection tests for ray tracing in graphics processors. In some embodiments, test circuitry is configured to perform intersection tests that operate on reduced-precision representations of rays that were generated by quantizing initial representations of the rays and reduced-precision representations of primitives that were generated by quantizing initial representations of the primitives. Some reduced-precision tests (e.g., for any-hit rays) may generate a definitive hit according to the initial representations. In this situation, graphics processing circuitry may record an intersection with the reduced-precision representation of the primitive for the ray based on the first result, without performing an intersection test for the first ray using the initial representation of the ray and the primitive. Disclosed techniques may advantageously reduce power consumption, improve performance, or both.

Abstract: One embodiment of a method for rendering one or more graphics images includes tracing one or more rays through a graphics scene; computing one or more surface normals associated with intersections of the one or more rays with one or more surfaces, where computing each surface normal includes: computing a plurality of intermediate surface normals associated with a plurality of adjacent voxels of a grid, and interpolating the plurality of intermediate surface normals; and rendering one or more graphics images based on the one or more surface normals.

Abstract: Methods, computer systems and computer programs for generating a virtual representation of an interior space such as a room are provided. Techniques for capturing and normalizing sets of points for polygon mesh generation that utilize augmented reality toolkits are also described.

Abstract: Devices and methods for using ray tracing to render similar but different objects in a scene are described which include rendering a second object using an overlay hierarchy tree. The overlay hierarchy tree comprises shared data from a base hierarchy tree comprising data representing a first object in the scene, a second hierarchy tree representing the second object in the scene, difference data representing a difference between the first object and the second object and indication information which indicates nodes of the overlay hierarchy tree comprising difference data.

Abstract: A computer-implemented method of constructing a ray tracing acceleration structure for a scene defined with respect to an overall coordinate system. The acceleration structure includes a top-level acceleration structure (TLAS) having leaf nodes referencing one or more instances of a bottom-level acceleration structures (BLAS). The method comprises defining one or more TLAS nodes, for each TLAS node, determining a first bounding volume and associating the node with a transformation matrix that maps between the first bounding volume and a second bounding volume in the overall coordinate system.

Abstract: Computer-implemented methods for rendering a volumetric dataset and a surface embedded in the volumetric dataset are described. One method includes performing a volume rendering process to generate a volume rendering of the volume. Based on the volume rendering process, depths of respective locations in the volume rendering are determined, and the depths stored in association with the respective locations. A surface rendering process generates a surface rendering of a surface using the depths and respective locations. The volume rendering and the surface rendering are combined into a combined rendering of the volume and surface. In another method, depths of the surface at respective locations with respect to the volume are determined and the depths are stored in association with the locations. A volume rendering process includes a shading process which uses the depths of the surface and the respective locations.

Abstract: A plurality of computing devices are communicatively coupled to each other via a network, and each of the plurality of computing devices is operably coupled to one or more of a plurality of storage devices. A plurality of failure resilient stripes is distributed across the plurality of storage devices such that each of the plurality of failure resilient stripes spans a plurality of the storage devices. A graphics processing unit is operable to access data files from the failure resilient stripes, while bypassing a kernel page cache. Furthermore, these data files may be accessed in parallel by the graphics processing unit.

Abstract: The present disclosure provides systems and methods that combine physics-based systems with machine learning to generate synthetic LiDAR data that accurately mimics a real-world LiDAR sensor system. In particular, aspects of the present disclosure combine physics-based rendering with machine-learned models such as deep neural networks to simulate both the geometry and intensity of the LiDAR sensor. As one example, a physics-based ray casting approach can be used on a three-dimensional map of an environment to generate an initial three-dimensional point cloud that mimics LiDAR data. According to an aspect of the present disclosure, a machine-learned model can predict one or more dropout probabilities for one or more of the points in the initial three-dimensional point cloud, thereby generating an adjusted three-dimensional point cloud which more realistically simulates real-world LiDAR data.

Abstract: This disclosure provides a method and apparatus for processing occlusion in an image, a device, and a computer storage medium. The method includes: determining a current viewpoint parameter used for drawing a current image frame; obtaining a predicted depth map matching the current viewpoint parameter as a target depth map of the current image frame; and determining an occlusion culling result of an object in the current image frame according to the target depth map.

Abstract: A CAD model comprises multiple parts forming an assembly. Per part, one or more test directions are determined. Per part and per test direction of the part, a blocking subset of parts is determined. For a part and test direction, a candidate set of candidate parts may be filtered via a view box. Based on the test direction, a ray set of border points associated with the part may be determined. A blocking subset may be determined from the candidate set based on ray tracing in the test direction from the border points of the ray set. A disassembly direction and one or more disassembly parts are selected from said multiple parts and the corresponding test directions based on the determined blocking subsets. An exploded view comprising a relative displacement of the one or more disassembly parts in the disassembly direction is created and displayed via a visualization means.

Abstract: A three-dimensional shape data processing apparatus includes a processor configured to divide a three-dimensional space including a three-dimensional shape constituted by one or more forming surfaces, which are flat surfaces or curved surfaces or include both flat surfaces and curved surfaces, into plural three-dimensional regions each having a predetermined size, specify, for each of the three-dimensional regions, one or more of the forming surfaces that interfere(s) with the three-dimensional region, and redivide each of the three-dimensional regions until a size of the three-dimensional region reaches a size necessary for reproduction of a property of a portion of the three-dimensional shape expressed by one or more of the forming surfaces that interfere(s) with the three-dimensional region.

Abstract: The present invention is generally directed to anatomically conforming apparatuses, and the creation, design, and fitting of such apparatuses. In at least one embodiment, the present invention relates to masks that require a conformal fit to a user's face, including, but not limited to, respirator and breathing masks, oxygen masks for both civil and military pilots, ventilation masks used in hazardous environments, and the like. One or more methods for clustering facial scans to design a finite set of mass-producible masks is also described, such that each individual in a given population can be assigned at least one mask in the set of masks that is anatomically conforming to that individual's specific facial geometry. Also described are one or more methods for fitting a face mask to a specific individual based on a 3-D scan of that individual's face.

Abstract: A hazard visualization system that can use artificial intelligence to identify locations at which hazards have occurred and a cause therein and to predict locations at which hazards may occur in the future is described herein. As a result, the hazard visualization system may reduce the likelihood of structural damage and/or loss of life that could otherwise occur due to natural disasters or other hazards. For example, the hazard visualization system can train an artificial intelligence model to predict the date, time, type, severity, path, and/or other conditions of a hazard that may occur at a geographic location. As another example, the hazard visualization system can train an artificial intelligence model to identify equipment or other infrastructure depicted in geographic images.