Abstract: While one type of input, either a mouse input or a joystick input, may be preferred for one type of a game, it may not be preferred, or even compatible, for another type of a game. Introduced herein is a game controller that employs a dedicated input, which is capable of the absolute accuracy of a mouse input or trackball input, but is also capable of measuring how far off center the input is (e.g., how far off center it has moved), and can also return to center when released, as is present in a joystick input. The introduced game controller integrates a touch sensing trackball to enjoy the benefits of both the mouse type input and joystick type input, in a single dedicated input, providing a user freedom to play any type of game without worrying about the compatibility of their game controllers.

Abstract: Raytracing can be used to generate high quality, physics-based water caustics patterns in real time. A caustics map is generate to represent locations and normals of points across a water surface. Rays from a light source that are reflected and refracted from these points, as determined by the locations and normals, and can generate hit points on a surface. Neighboring points can be used to help determine the resulting caustics pattern. In one embodiment, information for neighboring points in the caustics map can be used to generate scale factors for geometric regions to be projected onto the surface for each hit point. In another embodiment, these points serve as vertices of a caustic mesh that can be projected onto the surface, where the brightness at a primitive is determined by the size of the primitive area defined by the vertices of the caustics mesh.

Abstract: In various examples, the actual spatial properties of a virtual environment are used to produce, for a pixel, an anisotropic filter kernel for a filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment. Geometry of the virtual environment may be computed based at least in part on a projection of a light source onto a surface through an occluder, in order to determine a footprint that reflects a contribution of the light source to lighting conditions of the pixel associated with a point on the surface. The footprint may define a size, orientation, and/or shape of the anisotropic filter kernel and corresponding filter weights. The anisotropic filter kernel may be applied to the pixel to produce a graphically-rendered image of the virtual environment.

Abstract: In various examples, activation criteria and/or braking profiles corresponding to automatic emergency braking (AEB) systems and/or collision mitigation warning (CMW) systems may be determined using sensor data representative of an environment to a front, side, and/or rear of a vehicle. For example, activation criteria for triggering an AEB system and/or CMW system may be adjusted by leveraging the availability of additional information with regards to the surrounding environment of a vehicle—such as the presence of a trailing vehicle. In addition, the braking profile for the AEB activation may be adjusted based on information about the presence of and/or location of vehicles to the front, rear, and/or side of the vehicle. By adjusting the activation criteria and/or braking profiles of an AEB system, the potential for collisions with dynamic objects in the environment is reduced and the overall safety of the vehicle and its passengers is increased.

Abstract: The disclosure presents a technique for utilizing ray tracing to produce high quality visual scenes with shadows while minimizing computing costs. The disclosed technique can lower the number of rays needed for shadow region rendering and still maintain a targeted visual quality for the scene. In one example, a method for denoising a ray traced scene is disclosed that includes: (1) applying a pixel mask to a data structure of data from the scene, wherein the applying uses the scene at full resolution and pixels at the edge of a depth boundary change are identified using the pixel mask, (2) generating a penumbra mask using the data structure, (3) adjusting HitT values in the packed data buffer utilizing the penumbra mask, and (4) denoising the scene by reducing scene noise in the data of the data structure with adjusted HitT values.

Abstract: The autonomous vehicle generates an overlapped image by overlaying HD map data over sensor data and rendering the overlaid images. The visualization process is repeated as the vehicle drives along the route. The visualization may be displayed on a screen within the vehicle or at a remote device. The system performs reverse rendering of a scene based on map data from a selected point. For each line of sight originating at the selected point, the system identifies the farthest object in the map data. Accordingly, the system eliminates objects obstructing the view of the farthest objects in the HD map as viewed from the selected point. The system further allows filtering of objects using filtering criteria based on semantic labels. The system generates a view from the selected point such that 3D objects matching the filtering criteria are eliminated from the view.

Abstract: A parallel processing unit (e.g., a GPU), in some examples, includes a hardware scheduler and hardware arbiter that launch graphics and compute work for simultaneous execution on a SIMD/SIMT processing unit. Each processing unit (e.g., a streaming multiprocessor) of the parallel processing unit operates in a graphics-greedy mode or a compute-greedy mode at respective times. The hardware arbiter, in response to a result of a comparison of at least one monitored performance or utilization metric to a user-configured threshold, can selectively cause the processing unit to run one or more compute work items from a compute queue when the processing unit is operating in the graphics-greedy mode, and cause the processing unit to run one or more graphics work items from a graphics queue when the processing unit is operating in the compute-greedy mode. Associated methods and systems are also described.

Abstract: Object re-identification refers to a process by which images that contain an object of interest are retrieved from a set of images captured using disparate cameras or in disparate environments. Object re-identification has many useful applications, particularly as it is applied to people (e.g. person tracking). Current re-identification processes rely on convolutional neural networks (CNNs) that learn re-identification for a particular object class from labeled training data specific to a certain domain (e.g. environment), but that do not apply well in other domains. The present disclosure provides cross-domain disentanglement of id-related and id-unrelated factors. In particular, the disentanglement is performed using a labeled image set and an unlabeled image set, respectively captured from different domains but for a same object class.

Abstract: A communication method between a source device and a target device utilizes speculative connection setup between the source device and the target device, target-device-side packet ordering, and fine-grained ordering to remove packet dependencies.

Abstract: Estimating a three-dimensional (3D) pose and shape of an articulated body mesh is useful for many different applications including health and fitness, entertainment, and computer graphics. A set of estimated 3D keypoint positions for a human body structure are processed to compute parameters defining the pose and shape of a parametric human body mesh using a set of geometric operations. During processing, 3D keypoints are extracted from the parametric human body mesh and a set of rotations are computed to align the extracted 3D keypoints with the estimated 3D keypoints. The set of rotations may correctly position a particular 3D keypoint location at a “joint”, but an arbitrary number of rotations of the “joint” keypoint may produce a twist in a connection to a child keypoint. Rules are applied to the set of rotations to resolve ambiguous twists and articulate the parametric human body mesh according to the computed parameters.

Abstract: A system align point clouds obtained by sensors of a vehicle using kinematic iterative closest point with integrated motions estimates. The system receives lidar scans from a lidar mounted on the vehicle. The system derives point clouds from the lidar scan data. The system iteratively determines velocity parameters that minimize an aggregate measure of distance between corresponding points of the plurality of pairs of points. The system iteratively improves the velocity parameters. The system uses the velocity parameters for various purposes including for building high definition maps used for navigating the vehicle.

Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.

Abstract: A system, method, and computer program product are provided for simultaneously determining settings for a plurality of parameter variations. In use, a plurality of parameter variations associated with a device is identified, where the plurality of parameter variations are organized into a plurality of segments. Additionally, settings for each of the plurality of parameter variations are determined and consistency of the settings across the plurality of segments is ensured.

Abstract: A unified cache subsystem includes a data memory configured as both a shared memory and a local cache memory. The unified cache subsystem processes different types of memory transactions using different data pathways. To process memory transactions that target shared memory, the unified cache subsystem includes a direct pathway to the data memory. To process memory transactions that do not target shared memory, the unified cache subsystem includes a tag processing pipeline configured to identify cache hits and cache misses. When the tag processing pipeline identifies a cache hit for a given memory transaction, the transaction is rerouted to the direct pathway to data memory. When the tag processing pipeline identifies a cache miss for a given memory transaction, the transaction is pushed into a first-in first-out (FIFO) until miss data is returned from external memory. The tag processing pipeline is also configured to process texture-oriented memory transactions.

Abstract: Systems and methods that facilitate efficient and effective shadow image generation are presented. In one embodiment, a hard shadow generation system comprises a compute shader, pixel shader and graphics shader. The compute shader is configured to retrieve pixel depth information and generate projection matrix information, wherein the generating includes performing dynamic re-projection from eye-space to light space utilizing the pixel depth information. The pixel shader is configured to create light space visibility information. The graphics shader is configured to perform frustum trace operations to produce hard shadow information, wherein the frustum trace operations utilize the light space visibility information. The light space visibility information can be considered irregular z information stored in an irregular z-buffer.

Abstract: A cold plate that is configurable and for a datacenter liquid cooling system is disclosed. The cold plate includes a first section, a second section, and an intermediate layer, which is changeable and has first channels to enable flow of a coolant through the intermediate layer, and has second channels or at least one adapted second channel to concentrate the coolant or the flow of the coolant to at least one area within the configurable cold plate corresponding to at least a heat generating feature of an associated computing device.

Abstract: Approaches in accordance with various embodiments provide for fluid simulation with substantially reduced time and memory requirements with respect to conventional approaches. In particular, various embodiments can perform time and energy efficient, large scale fluid simulation on processing hardware using a method that does not solve for the Navier-Stokes equations to enforce incompressibility. Instead, various embodiments generate a density tensor and rigid body map tensor for a large number of particles contained in a sub-domain. Collectively, the density tensor and rigid body map may represent input channels of a network with three spatial-dimensions. The network may apply a series of operations to the input channels to predict an updated position and updated velocity for each particle at the end of a frame. Such approaches can handle tens of millions of particles within a virtually unbounded simulation domain, as compared to classical approaches that solve for the Navier-Stokes equations.

Abstract: A technique for performing data parallel training of a neural network model is disclosed that incorporates batch normalization techniques using partial populations to generate normalization parameters. The technique involves processing, by each processor of a plurality of processors in parallel, a first portion of a sub-batch of training samples allocated to the processor to generate activations for the first portion of the sub-batch. Each processor analyzes the activations and transmits statistical measures for the first portion to an additional processor that reduces the statistical measures from multiple processors to generate normalization parameters for a partial population of the training samples that includes the first portion from each of the plurality of processors. The normalization parameters are then transmitted back to each of the processors to normalize the activations for both the first portion and a second portion of the sub-batch of training samples allocated to each processor.

Abstract: According to an aspect of an embodiment, operations may comprise for each of the set of geographic X-positions, accessing an HD map of a geographical region surrounding the geographic X-position, determining a convergence range for the geographic X-position, and storing the convergence range for the geographic X-position in the HD map. The operations may also comprise accessing the HD map, predicting a next geographic X-position of a target vehicle, predicting a covariance of the predicted next geographic X-position, accessing the convergence range for the geographic X-position in the HD map closest to the predicted next geographic X-position, estimating a current geographic X-position of the target vehicle by performing a localization algorithm, and determining a confidence value for the estimated current geographic X-position of the target vehicle based on the predicted next geographic X-position, the predicted covariance, and the accessed convergence range.

Abstract: Machine learning systems and methods that learn glare, and thus determine gaze direction in a manner more resilient to the effects of glare on input images. The machine learning systems have an isolated representation of glare, e.g., information on the locations of glare points in an image, as an explicit input, in addition to the image itself. In this manner, the machine learning systems explicitly consider glare while making a determination of gaze direction, thus producing more accurate results for images containing glare.