Abstract: The present disclosure relates to using end-to-end differentiable pipeline for optimizing parameters of a base procedural material to generate a procedural material corresponding to a target physical material. For example, the disclosed systems can receive a digital image of a target physical material. In response, the disclosed systems can retrieve a differentiable procedural material for use as a base procedural material in response. The disclosed systems can compare a digital image of the base procedural material with the digital image of the target physical material using a loss function, such as a style loss function that compares visual appearance. Based on the determined loss, the disclosed systems can modify the parameters of the base procedural material to determine procedural material parameters for the target physical material. The disclosed systems can generate a procedural material corresponding to the base procedural material using the determined procedural material parameters.

Abstract: An adjusted image data generating device includes storage and an adjusting section. The storage stores color reference data of a color reference therein. The adjusting section generates adjusted image data by adjusting an object image for image data representing a color reference image and the object image so that color data of a color reference image matches the color reference data. The color reference image is an image of a color reference. The image data is an image of an object.

Abstract: The invention provides, in some aspects, a system for implementing a rule derived basis to display image sets. In various embodiments of the invention, the selection of the images to be displayed, the layout of the images, as well as the rendering parameters and styles can be determined using a rule derived basis. In an embodiment of the present invention, the user is presented with images displayed based on their preferences without having to first manually adjust parameters.

Abstract: Texture filtering in computer graphics calculates first and second pairs of texture-space basis vectors that correspond to first and second pairs of screen-space basis vectors transformed to texture space under a local approximation of a mapping between screen space and texture space. Based on differences in magnitudes of the vectors of the pairs of texture-space basis vectors, an angular displacement is determined between a selected pair of the first and second pairs of screen-space basis vectors and screen-space principal axes of the local approximation of the mapping that indicate maximum and minimum scale factors of the mapping. The determined angular displacement and the selected pair of screen-space basis vectors are used to generate texture-space principal axes, with a major axis associated with the maximum scale factor of the mapping and a minor axis associated with the minimum scale factor of the mapping. A texture is filtered using the major and minor axes.

Abstract: Interference-based augmented reality hosting platforms are presented. Hosting platforms can include networking nodes capable of analyzing a digital representation of scene to derive interference among elements of the scene. The hosting platform utilizes the interference to adjust the presence of augmented reality objects within an augmented reality experience. Elements of a scene can constructively interfere, enhancing presence of augmented reality objects; or destructively interfere, suppressing presence of augmented reality objects.

Abstract: A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.

Abstract: A processor for optimizing partial writes to compressed blocks is configured to identify that a write request targets less than an entirety of a compressed block of pixel data, identify, based on a compression key, a compressed segment of the compressed block of pixel data that includes a target of the write request, and decompress, responsive to the write request, only the identified compressed segment of the compressed block of pixel data.

Abstract: Devices, methods and techniques related to image rendering for ground-penetrating radar (GPR) systems are disclosed. In one example aspect, a method for producing one or more images associated with a GPR includes receiving information representative of signals received by the GPR, determining at least three frequency bands associated with the received information, assigning color values to the received information corresponding to the at least three frequency bands, and generating a color image for the one or more objects by combining the received information in all of the at least three frequency bands together such that the color values in the color image indicate a size of the one or more objects, a depth at which the one or more objects is buried underground, or an electrical permittivity of the one or more objects.

Abstract: Apparatus for visualization within a three-dimensional (3D) model and methods used therein are described, wherein the apparatus includes a processor and a memory communicatively connected to the processor, wherein the memory includes instructions configuring the processor to receive a query image, extract neural network encodings from the received query image, query a synthetic image repository for at least a matching synthetic image, and display an estimated region of interest within the 3D model, wherein the synthetic image repository includes a plurality of synthetic images and their extracted neural network encodings, each synthetic image therein corresponds to a region of interest in the 3D model, and querying the synthetic image repository includes comparing the extracted neural network encodings between the query image and synthetic images.

Abstract: Systems and methods are provided for color-coded visualization to aid in diagnosis and prognosis of Alzheimer's disease (AD). The color-coded visualization mechanism can be driven by an integrated machine learning (ML) model, which can take as its inputs neuroimaging (e.g., magnetic resonance imaging (MRI), positron emission tomography (PET)) data, neuropsychological test scores, the cerebrospinal fluid (CSF) biomarker, and/or risk factors. With these inputs, the ML model can generate a color-coded visualization of the disease state.

Abstract: A computer implemented method for rendering a page that includes one or more dynamic design elements into an output video is described. The method comprises processing the page to generate one or more layers, each layer being either a static layer associated with one or more static design elements of the page or a dynamic layer associated with a single dynamic design element of the page. Output frames are then generated using the layers and then encoded into the output video.

Abstract: The invention provides, in some aspects, a system for implementing a rule derived basis to display image sets. In various embodiments of the invention, the selection of the images to be displayed, the layout of the images, as well as the rendering parameters and styles can be determined using a rule derived basis. The rules are based on meta data of the examination as well as image content that is being analyzed by neuronal networks. In an embodiment of the present invention, the user is presented with images displayed based on their preferences without having to first manually adjust parameters.

Abstract: A data visualization overlay comprising a facility map including one or more zones; and one or more symbols representing one or more data points wherein the one or more symbols are aggregated in a helical display disposed on the one or more zones thereby allowing a readable representation of the one or more data points on the facility map.

Abstract: A method and system for augmented neurologic rehabilitation (ANR) of a patient is disclosed. The ANR system generates rhythmic auditory stimulus (RAS) and a visual augmented reality (AR) scene that are synchronized according to a common beat tempo and output to the patient during a therapy session. Sensor worn by the patient capture biomechanical data relating to repetitive movements performed by the patient in sync with the AR visual content and RAS. A critical thinking algorithm analyzes the sensor data to determine a spatial and temporal relationship of the patient's movements relative to the visual and audio elements and determine a level of entrainment of the patient and progression toward clinical/therapeutic goals. Additionally, a 3D AR modelling module configures the processor to dynamically adjust the augmented-reality visual and audio content output to the patient based on the determined level of entrainment and whether a training goal has been achieved.

Abstract: An image rendering method and apparatus, a device, and a medium. The method includes: determining a pre-captured initial rendering video stream for a background image; obtaining initial rendering coordinates of each rendering pixel in each initial rendering image frame in the video stream, and obtaining a rendering moment of each initial rendering image frame in the initial rendering video stream; determining the amount of noise of each rendering pixel at the corresponding rendering moment according to the corresponding initial rendering coordinates, a preset noise texture, and the corresponding rendering moment, and obtaining target rendering coordinates of each rendering pixel according to the corresponding amount of noise; and updating the initial rendering coordinates of each rendering pixel according to the corresponding target rendering coordinates to obtain a target rendering image, and rendering the background image according to a target rendering video stream composed of all target rendering images.

Abstract: A method and system for color mapping digital visual content for improved viewing by a color vision deficient observer includes receiving the digital visual content to be color mapped, clustering color values of the digital visual content into a plurality of color clusters, assigning each color cluster to a respective one of a set of target color values in which the set of target color values have increased visual distinguishability for the color vision deficient observer; and for each color cluster, mapping the color values of the color cluster to the target color value, thereby generating a color-mapped digital visual content. One or more regions of interest of the content can be identified and the color mapping may be applied onto to those regions of interest.

Abstract: A display system includes a display and a controller. The controller causes the display to display a third figure representing a relative relationship between a first figure indicating a direction of a working implement of a working machine and a second figure indicating a direction of a target topography from the working machine.

Abstract: A method for registering a two-dimensional image data set with a three-dimensional image data set of a body of interest is discloses herein. The method includes the following steps: adjusting a first virtual camera according to a distance parameter calculated corresponding to the two-dimensional image data set and the body of interest; rotating the first virtual camera according to an angle difference between a first vector and a second vector; and rotating the first virtual camera according to an angle which is corresponding to a maximum similarity value of a plurality of similarity values calculated in accordance with reconstructed images of the three-dimensional image data set which includes one generated by the first virtual camera and the others generated by other virtual cameras with different angles or different pixels from the one generated by the first virtual camera and the two-dimensional image data set.

Abstract: Devices, systems, and methods for sampling partially resident texture data. An instruction which includes a residency map descriptor is received. The instruction is executed to retrieve partially resident texture data from a mipmap stored in a memory based on the residency map descriptor. The residency map descriptor includes a residency map.

Abstract: A method, an electronic device, and a computer program product for generating a three-dimensional scene are provided in embodiments of the present disclosure. The method may include obtaining source image features from a plurality of two-dimensional source images associated with the three-dimensional scene to be generated. The method may further include obtaining editing features from an editing instruction input by a user for the three-dimensional scene, each of the editing features respectively forming a feature pair with each of the source image features. Furthermore, the method may include updating the source image features by maximizing a correlation coefficient of each of the feature pairs, and generating the three-dimensional scene based at least on the updated source image features. Embodiments of the present disclosure can realize arbitrary editing of a three-dimensional scene, thus enhancing the experience of human-computer interaction.