Abstract: The present disclosure relates to methods and apparatus for graphics processing. The apparatus can obtain at least one input image including a plurality of pixels. Additionally, the apparatus can determine shading information for each of the plurality of pixels in the at least one input image. The apparatus can also determine a shading map based on the determined shading information for each of the plurality of pixels in the at least one input image. In some aspects, the apparatus can generate at least one output image based on the at least one input image and the determined shading map. The apparatus can also enhance a quality of the at least one output image. In some aspects, the quality of the at least one output image can be enhanced based on machine learning. Further, the apparatus can generate the at least one input image including the plurality of pixels.

Abstract: A computer-implemented method for procedurally simulating braided strands of fibers may include, under the control of one or more computer systems configured with executable instructions, obtaining a set of parameters of the braided strands of the fibers, the set of parameters indicating a braid spine, generating, based at least in part on the set of parameters, a set of interlacing strand spines that follow the braid spine within a tolerance according to the set of parameters, and computing a set of first geometric structures corresponding to the set of interlacing strand spines.

Abstract: The present disclosure provides systems and methods for providing augmented reality experiences. Consistent with disclosed embodiments, one or more machine-learning models can be trained to selectively process image data. A pre-processor can be configured to receive image data provided by a user device and trained to automatically determine whether to select and apply a preprocessing technique to the image data. A classifier can be trained to identify whether the image data received from the pre-processor includes a match to one of a plurality of triggers. A selection engine can be trained to select, based on a matched trigger and in response to the identification of the match, a processing engine. The processing engine can be configured to generate an output using the image data, and store the output or provide the output to the user device or a client system.

Abstract: An augmented reality (AR) device supporting an AR is provided. The AR device includes a display, a communication circuit, at least one processor operatively connected to the display and the communication circuit, and a memory operatively connected to the at least one processor. The memory stores instructions that, when executed, cause the at least one processor to establish a connection with a user device storing a contact application and a message application, through the communication circuit, detect that the message application is executed, and display a first graphic user interface (GUI) and at least one avatar, which is disposed at a location adjacent to the first GUI and corresponds to at least one contact associated with the contact application or the message application, through the display in the AR.

Abstract: Selectively redacting an image by determining a set of attributes used by a machine learning model for an analysis, receiving image data detecting, by the one or more computer processors, a portion of the image data relevant to the analysis, the portion comprising at least some of the set of attributes, generating a synthetic portion from the portion, wherein the synthetic portion retains at least some of the attributes of the detected portion, replacing the portion with the synthetic portion, yielding redacted image data, and providing the redacted image data for analysis.

Abstract: Methods, systems, and computer-readable media for GPU code injection to summarize machine learning training data are disclosed. Training of a machine learning model is initiated using a graphics processing unit (GPU) associated with a machine learning training cluster. The training of the machine learning model generates tensor data in a memory of the GPU. The GPU determines a summary of the tensor data according to a reduction operator. The summary is smaller in size than the tensor data and is output by the GPU. A machine learning analysis system performs an analysis of the training of the machine learning model based at least in part on the summary of the tensor data. The machine learning analysis system detects one or more conditions associated with the training of the machine learning model based at least in part on the analysis.

Abstract: To generate 3D representation of a scene volume, the present invention combines the 3D skeleton approach and the shape from silhouette approach. The present invention efficiently works on complex scenes like sport events with multiple players in a stadium, with an ability to detect a wide number of interoperating 3D objects like multiple players.

Abstract: A method is performed at a moveable scanner with one or more optical sensors. The method includes scanning, using the moveable scanner, an object having a surface. The scanning generates color data from a plurality of orientations of the moveable scanner with respect to the object. The method further includes generating, using at least the color data, a pixel map of the surface of the object, the pixel map including, for each respective pixel of a plurality of pixels: a color value of a corresponding point on the surface of the object; and a value for a non-color property of the corresponding point on the surface of the object.

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.

Abstract: A system for rasterizing an image of a virtual environment, the system comprising a bounding volume hierarchy, BVH, obtaining unit operable to obtain a BVH representing one or more objects in the virtual environment, wherein each node of the BVH is associated with geometry information for the one or more objects at least partially contained within a bounding volume represented by that node, a frustum identification unit operable to identify a viewing frustum associated with a virtual camera defining a viewpoint within the virtual environment, a BVH identification unit operable to identify a BVH node associated with at least one bounding volume that is intersected by the frustum and a rasterization unit operable to rasterize an image of the virtual environment using the geometry information associated with the identified BVH node.

Abstract: A sensor simulation system may generate sensor data for use in simulations by rendering two-dimensional views of a three-dimensional simulated environment. In various examples, the sensor simulation system uses sensor dependency data to determine specific views to be re-rendered at different times during the simulation. The sensor simulation system also may generate unified views with multi-sensor data at each region (e.g., pixel) of the two-dimensional view for consumption by different sensor types. A hybrid technique may be used in some implementations in which rasterization is used to generate a view, after which ray tracing is used to align the view with a particular sensor. Spatial and temporal upsampling techniques also may be used, including depth-aware and velocity-aware analyses for simulated objects, to improve view resolution and reduce the frequency of re-rendering views.

Abstract: An image generation system comprising a bounding volume hierarchy, BVH, storage unit operable to store a BVH comprising a hierarchical structure of a plurality of triangles describing a virtual scene, a BVH position buffer operable to store data for identifying the location of one or more triangles within the BVH, and a fetch shader operable to identify vertex indices for use in rendering images, to obtain one or more triangles within the BVH corresponding to those vertex indices, and to provide vertex data corresponding to those triangles to a vertex shader operable to perform a vertex shading process.

Abstract: Devices, systems, methods, and media are described for adaptive scene augmentation of a point cloud frame for inclusion in a labeled point cloud dataset used for training a machine learned model for a prediction task for point cloud frames, such as object detection or segmentation. A formal method is described for generating new point cloud frames based on pre-existing annotated large-scale labeled point cloud frames included in a point cloud dataset to generate new, augmented point cloud frames. A policy is generated for large-scale data augmentation using detailed quantitative metrics such as confusion matrices. The policy is a detailed and stepwise set of rules, procedures, and/or conditions that may be used to generate augmented data specifically targeted to mitigate the existing inaccuracies in the trained model. The augmented point cloud frames may then be used to further train the model to improve the prediction accuracy of the model.

Abstract: A computer-implemented method and system for determining a localization of a digitally-modeled object with respect to a digitally-modeled space and performing volumetric queries. The method including retrieving or creating voxel representations of the object (OV) and of the space, partitioning these representations of the digitally-modeled object into sets of heart (OH) and border (OB) voxels, determining intersections between sets of voxels of the object and of the space, and based on said intersections, determining the localization of the digitally-modeled object with respect to the digitally-modeled space.

Abstract: The disclosed subject matter relates to a method for generating an orthogonal view of an object in a surrounding area, comprising the following steps: creating a location-based first 3D point cloud over a predefined angular range around a first location by way of a laser scanner; representing the object in a computer-generated representation; selecting a view direction and a view boundary in the computer-generated representation; projecting the first 3D point cloud, or a derived first 3D point cloud derived therefrom, counter to the view direction onto a plane defined by the view boundary; and outputting the first 3D point cloud, or the derived first 3D point cloud, projected onto the plane within the view boundary as an orthogonal view.