Abstract: Methods, systems, and computer-readable media for generating a cross-section of a 3D model are disclosed. An example method includes determining a cross-section plane intersecting the 3D model, performing ray-tracing by passing each of a plurality of rays through a corresponding pixel of a viewing plane such that each ray intersects the cross-section plane, determining one or more rays that are within a threshold distance of the 3D model at their respective points of intersection with the cross section plane, and highlighting pixels corresponding to the determined rays.

Abstract: Methods and systems for remote rendering of extended reality (XR) objects are described herein. A server may receive an image of a physical environment. The image may include different views of the physical environment around a client device. The server may render at least one surface of a virtual object based on the different views of the physical environment. The at least one surface may include a reflection of another object of the physical environment from a view point of the client device at the time the image was taken. The server may generate graphics including the rendered at least one surface. The server may send the generated graphics to the client device to enable display of a computer generated environment on the client device. The computer generated environment may include the at least one virtual object with an appearance of a reflective surface.

Abstract: An illustrative image processing system identifies a component of a three-dimensional (3D) object that is to be presented to a user. The image processing system then generates a set of two-dimensional (2D) images depicting the component of the 3D object from a set of vantage points tailored to the component. The image processing system incorporates one or more 2D images of this set of 2D images within a 2D atlas image associated with the 3D object. The image processing system provides the 2D atlas image to a volumetric rendering device configured to render, based on the 2D atlas image, a volumetric representation of the 3D object for presentation to the user. Corresponding methods and systems are also disclosed.

Abstract: Computer-implemented method for civil engineering including obtaining a mesh representing a terrain and computing a watershed segmentation of the terrain based on the mesh, the computing of the watershed segmentation including identifying one or more saddle points on the mesh, for each identified saddle point, identifying paths each ascending from the saddle point according to a direction of a local maximal slope around the saddle point, and a path descending from the saddle point according to a direction of a steepest slope around the saddle point, the identified ascending paths dividing the mesh into connected components, and, for each identified saddle point, merging each connected component of which bottom point is the saddle point with a connected component including the identified path descending from the saddle point according to a direction of a steepest slope. The merging yields at least a part of a basin.

Abstract: Embodiments described herein pertain to a machine-learning approach for shading. A system may determine a number of pixels associated with a viewpoint of a viewer. The system may determine, for each of the pixels, (1) a view direction based on the viewpoint and a pixel position of that pixel and (2) and a surface orientation of a surface visible to that pixel. The system may generate, using a first machine-learning model, a latent space representation of ambient lighting information associated with the pixels based on respective view directions and surface orientations. The system may determine color values for the pixels by processing the latent space representation of ambient lighting information using a second machine-learning model.

Abstract: A display method includes the following operations. Multiple first image data are received by a processor through a graphics card. Multiple first image data are analyzed based on an artificial intelligence model by the processor. Multiple second image data are transmitted to the display by the processor. Multiple second image data include multiple first image data, at least one compensation image data between adjacent two of multiple first image data, or combinations thereof.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating enriched light sources by utilizing surface-centric representations of three-dimensional surfaces. Specifically, the disclosed system utilizes a surface-centric re-parameterization that combines geometric and algebraic components of a sphere to model different light source types in a continuous range of lighting configurations. The disclosed systems utilize a set of intuitive parameters to determine a shape and emission parameters for generating an enriched light source. Additionally, the disclosed system provides a set of interactive light source controls to modify a position, orientation, shape, emittance, and lighting attenuation over distance of a light source within a three-dimensional environment. The disclosed system determines the light source controls based on sets of three-dimensional interaction primitives to control one or more parameters of the light source.

Abstract: An embodiment of an electronic processing system may include an application processor, persistent storage media communicatively coupled to the application processor, a graphics subsystem communicatively coupled to the application processor, a power budget analyzer to identify a power budget for one or more of the application processor, the persistent storage media, and the graphics subsystem, a target analyzer communicatively coupled to the graphics subsystem to identify a target for the graphics subsystem, and a parameter adjuster to adjust one or more parameters of the graphics subsystem based on one or more of the identified power budget and the identified target.

Abstract: A medical image processing apparatus comprises processing circuitry configured to: acquire a data volume to be compressed; acquire a function relating color value to each data value of the data volume; and change a compression rate per region of the data volume based on color values in each region.

Abstract: An animation system wherein a machine learning model is adopted to generate animated facial actions based on parameters obtained from a live actor. Specifically, the anatomical structure such as a facial muscle topology and a skull surface topology that are specific to the live actor may be used. A skull surface that is specific to a live actor based on facial scans of the live actor and generic tissue depth data. For example, the facial scans of the live actor may provide a skin surface topology of the live actor, based on which the skull surface underneath the skin surface can be derived by “offsetting” the skin surface with corresponding soft tissue depth at different sampled points on the skin surface.

Abstract: The present application provides a method and system for reconstructing transparent objects based on multi-wavelength light tracing, the method comprises calculating and obtaining a reverse light equation of one pixel point of a camera by using intrinsic parameters of camera calibration; placing a transparent object on a display screen, emitting, by a backlight lighting source, lights of two or more different wavelengths to the display screen, and recording, by the pixel point, position information of the lights of two or more different wavelengths on the display screen, respectively; translating the display screen along a direction perpendicular thereto, and calculating a rectilinear equation of light from a lower surface of the transparent object to the display screen of the lights of different wavelengths recorded by the pixel point.

Abstract: The present disclosure relates to a reproducing device, a reproducing method, a recording device, a recording method, a reproducing/recording device, a reproducing/recording method, and a program capable of supporting more appropriate 3D model display. A reproduction processing unit reproduces free visual point moving image content including a free visual point moving image stream and an edit data stream, and display of a 3D model arranged in a space recreated by the free visual point moving image stream in accordance with basic information set in edit data constituting the edit data stream is controlled with reference to additional information set in the edit data. The present technology can be applied to, for example, a reproducing device capable of reproducing free visual point moving image content.

Abstract: A method and system for generating two or three dimensional computer graphics images using multisample antialiasing (MSAA) is provided, which enables memory bandwidth to be conserved. For each of one or more pixels it is determined whether all of a plurality of sample areas of that pixel are located within a particular primitive. For those pixels where it is determined that all the sample areas of that pixel are located within that primitive, a value is stored in a multisample memory for a smaller number of the sample areas of that pixel than the total number of the sample areas of that pixel and data is stored indicating that all the sample areas of that pixel are located within that primitive.

Abstract: A computer-implemented method for digital processing is provided. A set of tristimulus values representing a first color in a color space are received. A first representation of a first spectral curve corresponding to the first color is determined, where the first spectral curve is within a gamut of solid reflectances. A second representation of a second spectral curve corresponding to the first color is determined where the second spectral curve contains at least one reflectance wavelength outside the gamut of solid reflectances. Based on selection criteria, the first representation or the second representation is selected. The selected representation is then applied during digital processing.

Abstract: There is provided a method of design and analysis of a geometric object comprising: receiving an initial definition of the geometric object in a coordinate system; generating a volumetric model according to the initial definition, the volumetric model comprises: volumetric cells each represented by one or more multivariate of three variables or more functions, and intra object general border surfaces in general orientation each defines topological adjacency between at least two of said plurality of volumetric cells.

Abstract: The disclosure is related to systems and methods for generating an animation with a perception of real depth from one or more images. In some embodiments, a computing server may receive an input image. The input image captures a scene. The computing server may generate a set of layers of images, which may include one or more processed images. A processed image may be a version of the input image. The computing server may generate one or more variable masks that are used for a superposition of the set of layers. The variable masks may include a plurality of regions specifying different compositions of the layers in the superposition. The computing server may generate an animation of the scene from the set of layers. The animation may include a composite frame generated from the set of layers of images superimposed according to the variable masks.

Abstract: A work request data system wherein a user a person such a homeowner to access and possess accurate information about the physical measurements of a structure or other object as derived from a three-dimensional model of the property. The interface generates the measurement through an extraction module.

Abstract: Presented here is a system and method to increase the speed of computation of a volumetric scattering render technique. The volumetric scattering can include path tracing which simulates interactions between a virtual ray of light and a volume. The interaction can include reflection of the virtual ray of light of a particle within the volume. The system can obtain a threshold number of interactions between a virtual ray of light and a three-dimensional object through which the virtual ray of light is traveling. As the system performs the simulation, the system can compare a number of the interactions to the threshold number. Upon determining that the number of interactions is equal to or exceeds the threshold number, the system can terminate the simulation and approximate interactions between the virtual ray of light and the volume using a second rendering technique that is computationally less expensive than simulating the interactions.

Abstract: A ray tracing unit is implemented in a graphics rendering system. The ray tracing unit comprises: processing logic configured to perform ray tracing operations on rays, a dedicated ray memory coupled to the processing logic and configured to store ray data for rays to be processed by the processing logic, an interface to a memory system, and control logic configured to manage allocation of ray data to either the dedicated ray memory or the memory system. Core ray data for rays to be processed by the processing logic is stored in the dedicated ray memory, and at least some non-core ray data for the rays is stored in the memory system. This allows core ray data for many rays to be stored in the dedicated ray memory without the size of the dedicated ray memory becoming too wasteful when the ray tracing unit is not in use.

Abstract: Techniques for representing a scene or map based on statistical data of captured environmental data are discussed herein. In some cases, the data (such as covariance data, mean data, or the like) may be stored as a multi-resolution voxel space that includes a plurality of semantic layers. In some instances, individual semantic layers may include multiple voxel grids having differing resolutions. Multiple multi-resolution voxel spaces may be merged to generate combined scenes based on detected voxel covariances at one or more resolutions.