Abstract: According to an aspect of an embodiment, operations may comprise obtaining a pose graph that comprises a plurality of nodes. The operations may also comprise dividing the pose graph into a plurality of pose subgraphs, each pose subgraph comprising one or more respective pose subgraph interior nodes and one or more respective pose subgraph boundary nodes. The operations may also comprise generating one or more boundary subgraphs based on the plurality of pose subgraphs, each of the one or more boundary subgraphs comprising one or more respective boundary subgraph boundary nodes and comprising one or more respective boundary subgraph interior nodes. The operations may also comprise obtaining an optimized pose graph by performing a pose graph optimization. The pose graph optimization may comprise performing a pose subgraph optimization of the plurality of pose subgraphs and performing a boundary subgraph optimization of the plurality of boundary subgraphs.

Abstract: Accesses between a processor and its external memory is reduced when the processor internally maintains a compressed version of values stored in the external memory. The processor can then refer to the compressed version rather than access the external memory. One compression technique involves maintaining a dictionary on the processor mapping portions of a memory to values. When all of the values of a portion of memory are uniform (e.g., the same), the value is stored in the dictionary for that portion of memory. Thereafter, when the processor needs to access that portion of memory, the value is retrieved from the dictionary rather than from external memory. Techniques are disclosed herein to extend, for example, the capabilities of such dictionary-based compression so that the amount of accesses between the processor and its external memory are further reduced.

Abstract: A method, computer readable medium, and system are disclosed for implementing automatic level-of-detail for physically-based materials. The method includes the steps of identifying a declarative representation of a material to be rendered, creating a reduced complexity declarative representation of the material by applying one or more term rewriting rules to the declarative representation of the material, and returning the reduced complexity declarative representation of the material.

Abstract: A neural network model receives color data for a sequence of images corresponding to a dynamic scene in three-dimensional (3D) space. Motion of objects in the image sequence results from a combination of a dynamic camera orientation and motion or a change in the shape of an object in the 3D space. The neural network model generates two components that are used to produce a 3D motion field representing the dynamic (non-rigid) part of the scene. The two components are information identifying dynamic and static portions of each image and the camera orientation. The dynamic portions of each image contain motion in the 3D space that is independent of the camera orientation. In other words, the motion in the 3D space (estimated 3D scene flow data) is separated from the motion of the camera.

Abstract: In various examples, a deep neural network (DNN) is trained for sensor blindness detection using a region and context-based approach. Using sensor data, the DNN may compute locations of blindness or compromised visibility regions as well as associated blindness classifications and/or blindness attributes associated therewith. In addition, the DNN may predict a usability of each instance of the sensor data for performing one or more operations—such as operations associated with semi-autonomous or autonomous driving. The combination of the outputs of the DNN may be used to filter out instances of the sensor data—or to filter out portions of instances of the sensor data determined to be compromised—that may lead to inaccurate or ineffective results for the one or more operations of the system.

Abstract: Artificial neural networks (ANNs) are computing systems that imitate a human brain by learning to perform tasks by considering examples. By representing an artificial neural network utilizing individual paths each connecting an input of the ANN to an output of the ANN, a complexity of the ANN may be reduced, and the ANN may be trained and implemented in a much faster manner when compared to an implementation using fully connected ANN graphs.

Abstract: Recurrent blurring may be used to render frames of a virtual environment, where the radius of a filter for a pixel is based on a number of successfully accumulated frames that correspond to that pixel. To account for rejections of accumulated samples for the pixel, ray-traced samples from a lower resolution version of a ray-traced render may be used to increase the effective sample count for the pixel. Parallax may be used to control the accumulation speed along with an angle between a view vector that corresponds to the pixel. A magnitude of one or more dimensions of a filter applied to the pixel may be based on an angle of a view vector that corresponds to the pixel to cause reflections to elongate along an axis under glancing angles. The dimension(s) may be based on a direction of a reflected specular lobe associated with the pixel.

Abstract: A gaze tracking system for use by the driver of a vehicle includes an opaque frame circumferentially enclosing a transparent field of view of the driver, light emitting diodes coupled to the opaque frame for emitting infrared light onto various regions of the driver's eye gazing through the transparent field of view, and diodes for sensing intensity of infrared light reflected off of various regions of the driver's eye.

Abstract: Techniques are disclosed for improving the throughput of ray intersection or visibility queries performed by a ray tracing hardware accelerator. Throughput is improved, for example, by releasing allocated resources before ray visibility query results are reported by the hardware accelerator. The allocated resources are released when the ray visibility query results can be stored in a compressed format outside of the allocated resources. When reporting the ray visibility query results, the results are reconstructed based on the results stored in the compressed format. The compressed format storage can be used for ray visibility queries that return no intersections or terminate on any hit ray visibility query. One or more individual components of allocated resources can also be independently deallocated based on the type of data to be returned and/or results of the ray visibility query.

Abstract: Various implementations of a current flattening circuit are disclosed, including those utilizing a feedback current regulator, a feedforward current regulator, and a constant current source.

Abstract: A remote device utilizes ray tracing to compute a light field for a scene to be rendered, where the light field includes information about light reflected off surfaces within the scene. This light field is then compressed utilizing lossless or lossy compression and one or more video compression techniques that implement temporal reuse, such that only differences between the light field for the scene and a light field for a previous scene are compressed. The compressed light field data is then sent to a client device that decompresses the light field data and uses such data to obtain the light field for the scene at the client device. This light field is then used by the client device to compute global illumination for the scene. The global illumination may be used to accurately render the scene at the mobile device, resulting in a realistic scene that is presented by the mobile device.

Abstract: A network device configured to perform scalable, in-network computations is described. The network device is configured to process pull requests and/or push requests from a plurality of endpoints connected to the network. A collective communication primitive from a particular endpoint can be received at a network device. The collective communication primitive is associated with a multicast region of a shared global address space and is mapped to a plurality of participating endpoints. The network device is configured to perform an in-network computation based on information received from the participating endpoints before forwarding a response to the collective communication primitive back to one or more of the participating endpoints.

Abstract: A technique for analyzing data in order to detect issues within a cloud-based service is disclosed. Host computing devices in a data center launch virtual machines, where at least some virtual machines run a pipelined stack for a streaming service. Virtual machines in the host computing devices generate event data including timestamps. Metadata generated by the pipelined stack during each streaming session is analyzed to identify deadzones in the corresponding host computing device, and the event data is processed to identify potential root causes of the corresponding deadzones. The event data can be generated by the virtual machine hosting the streaming service or by different virtual machines on the same host computing device. A distribution of events of each event type relative to the identified deadzones is determined and an operation of the host computing device can be adjusted based on the distribution.

Abstract: In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

Abstract: A method, computer readable medium, and system are disclosed for identifying residual video data. This data describes data that is lost during a compression of original video data. For example, the original video data may be compressed and then decompressed, and this result may be compared to the original video data to determine the residual video data. This residual video data is transformed into a smaller format by means of encoding, binarizing, and compressing, and is sent to a destination. At the destination, the residual video data is transformed back into its original format and is used during the decompression of the compressed original video data to improve a quality of the decompressed original video data.

Abstract: Latency of in-system test (IST) execution for a hardware component of an in-field (deployed) computing platform may be reduced when a value of a physical operating parameter can be changed without rebooting the computing platform. A test (e.g., patterns or vectors) is executed for varying values of the physical operating parameter (e.g., supply voltage, clock speed, temperature, noise magnitude/duration, operating current, and the like), providing the ability to detect faults in the hardware components.

Abstract: An IC package including an integrated circuit die having a major surface and one or more solder bumps located on the major surface in at least one corner region of the major surface and a substrate having a surface, the surface including bump pads thereon. The major surface of the integrated circuit die faces the substrate surface, the one or more solder bumps are bonded to individual ones of the bump pads to thereby form a bond joint, the major surface of the integrated circuit die has a footprint area of at least about 400 mm2. A ratio of a coefficient of thermal expansion of the substrate (CTEsub) to a coefficient of thermal expansion of the integrated circuit die (CTEdie) is at least about 3:1. A method of manufacturing an IC package is also disclosed.

Abstract: A power adapter has a solenoid actuated retaining latch controlled by an electronic circuit that detects the presence or absence of AC mains voltage. When the assembled AC-DC adapter and plug assembly are removed from the wall, the latch detects removal and unlocks the plug assembly for easy removal without undue force required by the user. The circuit is designed for minimal power consumption, and the solenoid only consumes power when it is engaging or disengaging the latch.

Abstract: A neural network architecture is disclosed for restoring noisy data. The neural network is a blind-spot network that can be trained according to a self-supervised framework. In an embodiment, the blind-spot network includes a plurality of network branches. Each network branch processes a version of the input data using one or more layers associated with kernels that have a receptive field that extends in a particular half-plane relative to the output value. In one embodiment, the versions of the input data are offset in a particular direction and the convolution kernels are rotated to correspond to the particular direction of the associated network branch. In another embodiment, the versions of the input data are rotated and the convolution kernel is the same for each network branch. The outputs of the network branches are composited to de-noise the image. In some embodiments, Bayesian filtering is performed to de-noise the input data.

Abstract: In general, data is susceptible to errors caused by faults in hardware (i.e. permanent faults), such as faults in the functioning of memory and/or communication channels. To detect errors in data caused by hardware faults, the error correcting code (ECC) was introduced, which essentially provides a sort of redundancy to the data that can be used to validate that the data is free from errors caused by hardware faults. In some cases, the ECC can also be used to correct errors in the data caused by hardware faults. However, the ECC itself is also susceptible to errors, including specifically errors caused by faults in the ECC logic. A method, computer readable medium, and system are thus provided for securing against errors in an ECC.