Abstract: Approaches presented herein can reduce temporal lag that may be introduced in a generated image sequence that utilizes temporal accumulation for denoising in dynamic scenes. A fast historical frame can be generated along with a full historical frame generated for a denoising process, with the fast historical frame being accumulated using an exponential moving average with a significantly higher blend weight. This fast history frame can be used to determine a clamping window that can be used to clamp a corresponding full historical value before, or after, reprojection. The fast historical blend weight can be adjusted to control the amount of noise versus temporal lag in an image sequence. In some embodiments, differences between fast and full historical values can also be used to determine an amount of spatial filtering to be applied.

Abstract: In various examples, detected object data representative of locations of detected objects in a field of view may be determined. One or more clusters of the detected objects may be generated based at least in part on the locations and features of the cluster may be determined for use as inputs to a machine learning model(s). A confidence score, computed by the machine learning model(s) based at least in part on the inputs, may be received, where the confidence score may be representative of a probability that the cluster corresponds to an object depicted at least partially in the field of view. Further examples provide approaches for determining ground truth data for training object detectors, such as for determining coverage values for ground truth objects using associated shapes, and for determining soft coverage values for ground truth objects.

Abstract: Systems and methods for efficient lossless compression of captured raw image information are presented. A method can comprise: receiving raw image data from an image capture device, segregating the pixel data into a base layer portion and an enhanced layer portion, reconfiguring the base layer portion expressed in the first color space values from a raw capture format into a pseudo second color space compression mechanism compatible format, and compressing the reconfigured base layer portion of first color space values. The raw image data can include pixel data are expressed in first color space values. The segregation can be based upon various factors, including a compression benefits analysis of a boundary location between the base layer portion and enhanced layer portion. The reconfiguring the base layer portion can include separating the base layer portion based upon multiple components within the raw data; and forming base layer video frames from the multiple components.

Abstract: A datacenter cooling system is disclosed. The system includes a first cooling loop with a heat exchanger to exchange heat with a second cooling loop. The second cooling loop includes a cooling distribution unit (CDU) to exchange heat between the second cooling loop and a primary cooling loop.

Abstract: Techniques are disclosed for tracking memory page accesses in a unified virtual memory system. An access tracking unit detects a memory page access generated by a first processor for accessing a memory page in a memory system of a second processor. The access tracking unit determines whether a cache memory includes an entry for the memory page. If so, then the access tracking unit increments an associated access counter. Otherwise, the access tracking unit attempts to find an unused entry in the cache memory that is available for allocation. If so, then the access tracking unit associates the second entry with the memory page, and sets an access counter associated with the second entry to an initial value. Otherwise, the access tracking unit selects a valid entry in the cache memory; clears an associated valid bit; associates the entry with the memory page; and initializes an associated access counter.

Abstract: Embodiments relate to methods for efficiently encoding sensor data captured by an autonomous vehicle and building a high definition map using the encoded sensor data. The sensor data can be LiDAR data which is expressed as multiple image representations. Image representations that include important LiDAR data undergo a lossless compression while image representations that include LiDAR data that is more error-tolerant undergo a lossy compression. Therefore, the compressed sensor data can be transmitted to an online system for building a high definition map. When building a high definition map, entities, such as road signs and road lines, are constructed such that when encoded and compressed, the high definition map consumes less storage space. The positions of entities are expressed in relation to a reference centerline in the high definition map. Therefore, each position of an entity can be expressed in fewer numerical digits in comparison to conventional methods.

Abstract: A system for data and clock recovery includes a timing error detector, a phase detector, and a phase increment injector. The phase increment injector may be used to determine an increment to affect an output of the phase detector or a clocking element. A sign of the increment is determined from a sign or direction of an accumulated version of a clock and data recovery gradient value.

Abstract: In various examples, one or more components or regions of a processing unit—such as a processing core, and/or component thereof—may be tested for faults during deployment in the field. To perform testing while in deployment, the state of a component subject to test may be retrieved and/or stored during the test to maintain state integrity, the component may be clamped to communicatively isolate the component from other components of the processing unit, a test vector may be applied to the component, and the output of the component may be compared against an expected output to determine if any faults are present. The state of the component may be restored after testing, and the clamp removed, thereby returning the component to its operating state without a perceivable detriment to operation of the processing unit in deployment.

Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.

Abstract: Techniques to generate driving scenarios for autonomous vehicles characterize a path in a driving scenario according to metrics such as narrowness and effort. Nodes of the path are assigned a time for action to avoid collision from the node. The generated scenarios may be simulated in a computer.

Abstract: Techniques to characterize driving scenarios for autonomous vehicles characterize a path in a driving scenario according to metrics such as narrowness and effort. The scenarios may be characterized using a tree-based or tensor-based approach.

Abstract: A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include opaque and alpha triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to determine primitives intersected by the ray, and return intersection information to a streaming multiprocessor for further processing. The hardware-based traversal coprocessor is configured to omit reporting of one or more primitives the ray is determined to intersect. The omitted primitives include primitives which are provably capable of being omitted without a functional impact on visualizing the virtual scene.

Abstract: In modeling contact between two or more objects (such as a robotic arm placing a block on a stack of blocks) or articulations of a series of linked joints (such as modeling a backhoe), current techniques can introduce additional energy into the system or fail to resolve a constraint imposed on the system. The current techniques attempt to resolve these issues, for example, by using very small time steps. Very small time steps, however, can significantly increase computational costs of the modeling simulation. The disclosed simulation system for rigid bodies uses a time interval to reduce linearization artifacts due to the small time steps and reduce computational costs with faster solver convergence by permitting more efficient bias calculations. High mass handling can also be improved through the more efficient bias calculations.

Abstract: A neural network may be used to determine corner points of a skewed polygon (e.g., as displacement values to anchor box corner points) that accurately delineate a region in an image that defines a parking space. Further, the neural network may output confidence values predicting likelihoods that corner points of an anchor box correspond to an entrance to the parking spot. The confidence values may be used to select a subset of the corner points of the anchor box and/or skewed polygon in order to define the entrance to the parking spot. A minimum aggregate distance between corner points of a skewed polygon predicted using the CNN(s) and ground truth corner points of a parking spot may be used simplify a determination as to whether an anchor box should be used as a positive sample for training.

Abstract: Methods and systems are described in some examples for changing the traversal of an acceleration data structure in a highly dynamic query-specific manner, with each query specifying test parameters, a test opcode and a mapping of test results to actions. In an example ray tracing implementation, traversal of a bounding volume hierarchy by a ray is performed with the default behavior of the traversal being changed in accordance with results of a test performed using the test opcode and test parameters specified in the ray data structure and another test parameter specified in a node of the bounding volume hierarchy. In an example implementation a traversal coprocessor is configured to perform the traversal of the bounding volume hierarchy.

Abstract: Memory, used by a computer to store data, is generally prone to faults, including permanent faults (i.e. relating to a lifetime of the memory hardware), and also transient faults (i.e. relating to some external cause) which are otherwise known as soft errors. Since soft errors can change the state of the data in the memory and thus cause errors in applications reading and processing the data, there is a desire to characterize the degree of vulnerability of the memory to soft errors. In particular, once the vulnerability for a particular memory to soft errors has been characterized, cost/reliability trade-offs can be determined, or soft error detection mechanisms (e.g. parity) may be selectively employed for the memory. In some cases, memory faults can be diagnosed by redundant execution and a diagnostic coverage may be determined.

Abstract: Techniques are disclosed for reducing the latency between the completion of a producer task and the launch of a consumer task dependent on the producer task. Such latency exists when the information needed to launch the consumer task is unavailable when the producer task completes. Thus, various techniques are disclosed, where a task management unit initiates the retrieval of the information needed to launch the consumer task from memory in parallel with the producer task being launched. Because the retrieval of such information is initiated in parallel with the launch of the producer task, the information is often available when the producer task completes, thus allowing for the consumer task to be launched without delay. The disclosed techniques, therefore, enable the latency between completing the producer task and launching the consumer task to be reduced.

Abstract: The various embodiments of the present disclosure are directed towards methods for tone mapping High-Dynamic-Range (HDR) image data, as well as controlling the brightness of the image encoded by HDR the image data and/or the tone-mapped image data. HDR image is captured. A tone mapping function for the HDR image data is generated. To generate the tone mapping function, control points are dynamically determined based on an analysis of the HDR image data. The tone mapping function is fit to the control points. The tone mapping function is a non-linear function, and is described by a curve in a plane. The shape of the curve is constrained by a line generated from a portion of the control points. The tone mapping function is applied to the HDR image data. A color-compression is applied to the tone mapped image data to generate Standard Dynamic Range or Low Dynamic Range image data.

Abstract: In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

Abstract: In embodiments of the invention, an apparatus may include a display comprising a plurality of pixels and a computer system coupled with the display and operable to instruct the display to display images. The apparatus may further include an SLM array located adjacent to the display and comprising a plurality of SLMs, wherein the SLM array is operable to produce a light field by altering light emitted by the display to simulate an object that is in focus to an observer while the display and the SLM array are located within a near-eye range of the observer.