Abstract: In a graphics processing system comprising a graphics processor, a main memory, and a memory management unit, when rendering a frame that represents a view of a scene comprising one or more objects using a ray tracing process and the ray tracing process requires a traversal of a ray tracing acceleration data structure indicative of the distribution of geometry for the scene being rendered to determine geometry for the scene that may be intersected by a ray, at least part of the traversal of the ray tracing acceleration data structure is performed by the memory management unit (MMU).

Abstract: A building detection model is applied to identify a footprint of a building based on a first dataset. The building characterization model is applied to identify one or more derived characteristics of the building based on the footprint. A building area is determined based on the footprint and at least one of the one or more derived characteristics of the building. A record is created including an indicator of a geographic area, the building area, and the one or more derived characteristics of the building. A processing request is generated based on the record. One or more derived characteristics of the building are compared with one or more corresponding values of property data from a third-party data source to identify a mismatch. A data accuracy verification request is output based on the mismatch.

Abstract: Disclosed are techniques for generating a photorealistic image by augmenting or compositing at least a portion of a physical structure (e.g., a house) depicted in a two-dimensional (2D) image with synthetic image data. Additionally, disclosed are techniques for augmenting the depicted physical structure using a minimum amount of three-dimensional (3D) geometric data and applying a scene effect to the synthetic image data to create a photorealistic effect.

Abstract: A computer-implemented method for 3D reconstruction including obtaining 2D images and, for each 2D image, camera parameters which define a perspective projection. The 2D images all represent a same real object. The real object is fixed. The method also includes obtaining, for each 2D image, a smooth map. The smooth map has pixel values, and each pixel value represents a measurement of contour presence. The method also includes determining a 3D modeled object that represents the real object. The determining iteratively optimizes energy. The energy rewards, for each smooth map, projections of silhouette vertices of the 3D modeled object having pixel values representing a high measurement of contour presence. This forms an improved solution for 3D reconstruction.

Abstract: An electronic device receives a set of 2D images comprising at least first 2D image of an object of interest and detects a plurality of 2D landmarks on the first 2D image. The detected plurality of 2D landmarks corresponds to shape-features of the object of interest. The electronic device aligns a first three-dimensional (3D) shape model of a reference object by fitting 2D landmarks of the first 3D shape model to the detected plurality of 2D landmarks. The electronic device estimates texture mapping information between the object of interest and the aligned first 3D shape model and generates a dataset by including the first 2D image, the aligned first 3D shape model, and the estimated texture mapping information as a first sample of the dataset. Based on the generated dataset, the electronic device trains a neural network model on a task of 3D reconstruction from a single 2D image.

Abstract: Embodiments of provide systems, methods, and computer storage media for rendering multicolored vector content using pre-computed scalar fields, such as images or textures. In an example implementation, multicolored vector content is processed to generate a representation of three scalar fields: an unsigned distance field, a field of region IDs, and a color plane (also called a color field or a color texture). These three fields are pre-computed prior to rendering (e.g., outside of a rendering loop), and then subsequently used (e.g., by a GPU as textures) to render an approximation of the multicolored vector content.

Abstract: Disclosed are systems and methods for splat filling a three-dimensional (“3D”) model using semi-measured data. The splat filling includes generating measured data points for a 3D representation of a scene with positions that are measured from scanning the scene, and with color values defined from measured color values of used pixels from a two-dimensional (“2D”) of the scene. The splat filling includes generating a semi-measured data point based on an unused pixel of the 2D image. The position of the semi-measured data point is derived based on a separation between the unused pixel and one or more used pixels of the 2D image, and based on the positions of measured data points that are defined with the measured color values of the one or more pixels. The color values of the semi-measured data point are defined directly from the measured color values associated with the unused pixel.

Abstract: The embodiments of the present disclosure provide a gaze point calculation method, apparatus and device. The method includes: determining a 3D model of a first scene; obtaining a first panoramic image captured in the first scene, the first panoramic image includes a face image of a face; determining a spatial location of the face according to the first panoramic image; determining a gaze direction corresponding to the face according to the first panoramic image; and determining an eye gaze target according to the 3D model, the spatial location and the gaze direction. The accuracy of tracking the eye gaze in 3D model is improved.

Abstract: Disclosed herein are aspects for altering avatar backgrounds and rendering volumetric avatars in a three-dimensional virtual environment. An aspect begins by receiving, from a first device of a first user, configuration settings specifying how a background of a first user's avatar is to be presented to a second user in the 3D virtual environment. The aspect continues by capturing a video stream of the first user and altering portions of the video stream. The configuration settings and the video stream with the altered background are used to render the first user's avatar. Another aspect begins by receiving configuration settings and a video stream with a background. The aspect continues by rendering a front surface, back surface, and side surface of an avatar based on the configuration settings and video stream.

Abstract: A computer system for dynamic generation of custom color selections receives from a user an indication of a target color. The computer system also identifies a location of the target color within a mathematically-defined color space. The computer system identifies a location of a second color within the mathematically-defined color space. Additionally, the computer system generates a first golden triangle within the mathematically-defined color space. The location of the target color comprises a first vertex of the first golden triangle. The location of the second color comprises a second vertex of the first golden triangle. A location of a third color comprises a third vertex of the first golden triangle. The computer system then displays on a user interface an indication of the target color, the second color, and the third color.

Abstract: Several embodiments of scalable image processing systems and methods are disclosed herein whereby color management processing of source image data to be displayed on a target display is changed according to varying levels of metadata.

Abstract: This specification describes systems and methods for generating a mapping of a physical space from point cloud data for the physical space. The methods can include receiving the point cloud data for the physical space, filtering the point cloud data to, at least, remove sparse points from the point cloud data, aligning the point cloud data along x, y, and z dimensions that correspond to an orientation of the physical space, and classifying the points in the point cloud data as corresponding to one or more types of physical surfaces. The methods can also include identifying specific physical structures in the physical space based, at least in part, on classifications for the points in the point cloud data, and generating the mapping of the physical space to identify the specific physical structures and corresponding contours for the specific physical structures within the orientation of the physical space.

Abstract: Aspects presented herein relate to methods and devices for graphics processing including an apparatus, e.g., a GPU. The apparatus may receive a plurality of primitives associated with one or more frames in a scene, a portion of the scene being associated with an upscaled sample space and/or a downscaled sample space. The apparatus may also perform a binning pass for the plurality of primitives, the binning pass being associated with an unscaled sample space, where the binning pass sorts each of the primitives into one or more bins associated with each of the one or more frames. Further, the apparatus may perform one of one or more rendering passes for each of the one or more bins. The apparatus may also rasterize each of the plurality of primitives based on at least one of the upscaled sample space or the downscaled sample space.

Abstract: Disclosed herein is a microparticle analyzing apparatus including a detecting portion configured to simultaneously detect a fluorescence generated from a microparticle in plural wavelength regions and a displaying portion configured to display thereon detection results in the plural wavelength regions in a form of a spectrum.

Abstract: Estimating emotion may include obtaining an image of at least part of a face, and applying, to the image, an expression convolutional neural network (“CNN”) to obtain a latent vector for the image, where the expression CNN is trained from a plurality of pairs each comprising a facial image and a 3D mesh representation corresponding to the facial image. Estimating emotion may further include comparing the latent vector for the image to a plurality of previously processed latent vectors associated with known emotion types to estimate an emotion type for the image.

Abstract: Methods and systems for displaying information in augmented reality are described. In one embodiment, a system comprises a camera, a memory, a display, and a processor configured to (a) detect a first prescription drug in a field of view of a camera by detecting a glyph printed on a label on a container of the first prescription drug, (b) determine a first identifier associated with the first prescription drug using optical character recognition, (c) determine whether a user has access to additional data about the first prescription drug, (d) request the additional data about the first prescription drug from a database, and (e) display the additional data in augmented reality adjacent to the first prescription drug on the display such that the additional data moves when the field of view of the camera changes such that the additional data remains displayed adjacent to the first prescription drug.

Abstract: Embodiments of a method and apparatus for generating a virtual avatar, a device and a storage medium are provided. The method may include: determining a template coefficient of a target face in a to-be-processed image based on at least two real face feature templates; and determining a virtual avatar of the target face according to the template coefficient and at least two virtual face feature templates associated with the at least two real face feature templates.

Abstract: A spinal correction rod implant manufacturing process includes: estimating a targeted spinal correction rod implant shape based on a patient specific spine shape correction and including spine 3D modeling, one or more simulation loops each including: first simulating an intermediate spinal correction rod implant shape from modeling mechanical interaction between the patient specific spine and: either, for the first simulation, the implant shape, or, for subsequent simulation, if any, an overbent implant shape resulting from the previous simulation loop, a second simulation of an implant shape overbending applied to the targeted spinal correction rod implant shape producing an overbent spinal correction rod implant shape representing a difference between: either, for the first loop, the targeted spinal correction rod implant shape, or, for subsequent loop, if any, the overbent spinal correction rod implant shape resulting from the previous simulation loop, and the intermediate spinal correction rod implant sha

Abstract: Systems and methods are disclosed for blood flow simulation. For example, a method may include performing a plurality of blood flow simulations using a first model of vascular blood flow, each of the plurality of blood flow simulations simulating blood flow in a vasculature of a patient or a geometry based on the vasculature of the patient; based on results of the plurality of blood flow simulations, generating a response surface mapping one or more first parameters of the first model to one or more second parameters of a reduced order model of vascular blood; determining values for the one or more parameters of the reduced order model mapped, by the response surface, from parameter values representing a modified state of the vasculature; and performing simulation using the reduced order model parameterized by the determined values, to determine a blood flow characteristic of the modified state of the vasculature.

Abstract: A three-dimensional data creation method includes: creating first three-dimensional data from information detected by a sensor; receiving encoded three-dimensional data that is obtained by encoding second three-dimensional data; decoding the received encoded three-dimensional data to obtain the second three-dimensional data; and merging the first three-dimensional data with the second three-dimensional data to create third three-dimensional data.