Abstract: Systems and methods are disclosed related to synthetic bracketing for exposure correction. A deep learning based method and system produces a set of differently exposed images from a single input image. The images in the set may be combined to produce an output image with improved global and local exposure compared with the input image. An image encoder applies learned parameters to each input image to generate a set of image features including local exposure estimates for each of two or more regions of the input image and a low resolution latent representation of the input image. A decoder receives the local exposure estimates, the latent representation, and target enhancements that are processed to generate synthesized transformations. When applied to the input image, the synthesized transformations produce the set of transformed images. Each transformed image is a version of the input image synthesized to correspond to a respective target enhancement.

Abstract: One or more embodiments include receiving one or more frames of a live video captured by a video capturing device, wherein the one or more frames include a current frame that is most-recently captured, identifying a set of reference frames included in the one or more frames based on at least the current frame, wherein each frame in the set of reference frames has a different exposure level relative to the current frame, determining, using one or more neural networks, a set of missing details for one or more regions of the current frame based on the set of reference frames, generating an updated version of the current frame based on the set of details, and outputting the updated version of the current frame in real-time.

Abstract: In various examples, historical trajectory information of objects in an environment may be tracked by an ego-vehicle and encoded into a state feature. The encoded state features for each of the objects observed by the ego-vehicle may be used—e.g., by a bi-directional long short-term memory (LSTM) network—to encode a spatial feature. The encoded spatial feature and the encoded state feature for an object may be used to predict lateral and/or longitudinal maneuvers for the object, and the combination of this information may be used to determine future locations of the object. The future locations may be used by the ego-vehicle to determine a path through the environment, or may be used by a simulation system to control virtual objects—according to trajectories determined from the future locations—through a simulation environment.

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: A technique for dynamically configuring and executing an augmented neural network in real-time according to performance constraints also maintains the legacy neural network execution path. A neural network model that has been trained for a task is augmented with low-compute “shallow” phases paired with each legacy phase and the legacy phases of the neural network model are held constant (e.g., unchanged) while the shallow phases are trained. During inference, one or more of the shallow phases can be selectively executed in place of the corresponding legacy phase. Compared with the legacy phases, the shallow phases are typically less accurate, but have reduced latency and consume less power. Therefore, processing using one or more of the shallow phases in place of one or more of the legacy phases enables the augmented neural network to dynamically adapt to changes in the execution environment (e.g., processing load or performance requirement).

Abstract: In various examples, historical trajectory information of objects in an environment may be tracked by an ego-vehicle and encoded into a state feature. The encoded state features for each of the objects observed by the ego-vehicle may be used—e.g., by a bi-directional long short-term memory (LSTM) network—to encode a spatial feature. The encoded spatial feature and the encoded state feature for an object may be used to predict lateral and/or longitudinal maneuvers for the object, and the combination of this information may be used to determine future locations of the object. The future locations may be used by the ego-vehicle to determine a path through the environment, or may be used by a simulation system to control virtual objects—according to trajectories determined from the future locations—through a simulation environment.

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 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: A method for performing a Tree-Search (TS) on an environment is provided. The method comprises generating a tree for a current state of the environment based on a TS policy, determining a corrected TS policy, and determining an action to apply to the environment based on the corrected TS policy. The tree comprises a plurality of nodes including a root node among the plurality of nodes corresponding to the current state of the environment. Each node other than the root node among the plurality of nodes corresponding to an estimated future state of the environment. The plurality of nodes in the tree are connected by a plurality of edges. Each edge among the plurality of edges is associated with an action causing a transition from a first state to a different sate of the environment.

Abstract: In various examples, historical trajectory information of objects in an environment may be tracked by an ego-vehicle and encoded into a state feature. The encoded state features for each of the objects observed by the ego-vehicle may be used—e.g., by a bi-directional long short-term memory (LSTM) network—to encode a spatial feature. The encoded spatial feature and the encoded state feature for an object may be used to predict lateral and/or longitudinal maneuvers for the object, and the combination of this information may be used to determine future locations of the object. The future locations may be used by the ego-vehicle to determine a path through the environment, or may be used by a simulation system to control virtual objects—according to trajectories determined from the future locations—through a simulation environment.

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: Apparatuses, systems, and techniques to detect cheating in a computer game. In at least one embodiment, one or more circuits use one or more neural networks to detect cheating by one or more users of a computer game based, at least in part, on one or more images generated by the computer game.

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: Apparatuses, systems, and techniques are presented to modify media content using inferred attention. In at least one embodiment, a network is trained to predict a gaze of one or more users on one or more image features based, at least in part, on one or more prior gazes of the one or more users, wherein the prediction is to be used to modify at least one of the one or more image features.

Abstract: Sensors measure information about actors or other objects near an object, such as a vehicle or robot, to be maneuvered. Sensor data is used to determine a sequence of possible actions for the maneuverable object to achieve a determined goal. For each possible action to be considered, one or more probable reactions of the nearby actors or objects are determined. This can take the form of a decision tree in some embodiments, with alternative levels of nodes corresponding to possible actions of the present object and probable reactive actions of one or more other vehicles or actors. Machine learning can be used to determine the probabilities, as well as to project out the options along the paths of the decision tree including the sequences. A value function is used to generate a value for each considered sequence, or path, and a path having a highest value is selected for use in determining how to navigate the object.

Abstract: Sensors measure information about actors or other objects near an object, such as a vehicle or robot, to be maneuvered. Sensor data is used to determine a sequence of possible actions for the maneuverable object to achieve a determined goal. For each possible action to be considered, one or more probable reactions of the nearby actors or objects are determined. This can take the form of a decision tree in some embodiments, with alternative levels of nodes corresponding to possible actions of the present object and probable reactive actions of one or more other vehicles or actors. Machine learning can be used to determine the probabilities, as well as to project out the options along the paths of the decision tree including the sequences. A value function is used to generate a value for each considered sequence, or path, and a path having a highest value is selected for use in determining how to navigate the object.

Abstract: One embodiment of a method includes adjusting a plurality of hyperparameters corresponding to a plurality of neural networks trained asynchronously relative to each other using a plurality of computer systems. The method further includes asynchronously measuring one or more performance metrics associated with the plurality of neural networks being trained. The method further includes ceasing the adjusting of the plurality of hyperparameters corresponding to one or more of the plurality of neural networks if the one or more performance metrics associated with the one or more of the plurality of neural networks are below a threshold.

Abstract: In various examples, historical trajectory information of objects in an environment may be tracked by an ego-vehicle and encoded into a state feature. The encoded state features for each of the objects observed by the ego-vehicle may be used—e.g., by a bi-directional long short-term memory (LSTM) network—to encode a spatial feature. The encoded spatial feature and the encoded state feature for an object may be used to predict lateral and/or longitudinal maneuvers for the object, and the combination of this information may be used to determine future locations of the object. The future locations may be used by the ego-vehicle to determine a path through the environment, or may be used by a simulation system to control virtual objects—according to trajectories determined from the future locations—through a simulation environment.

Abstract: One embodiment of the present invention sets forth a technique for estimating a head pose of a user. The technique includes acquiring depth data associated with a head of the user and initializing each particle included in a set of particles with a different candidate head pose. The technique further includes performing one or more optimization passes that include performing at least one iterative closest point (ICP) iteration for each particle and performing at least one particle swarm optimization (PSO) iteration. Each ICP iteration includes rendering the three-dimensional reference model based on the candidate head pose associated with the particle and comparing the three-dimensional reference model to the depth data. Each PSO iteration comprises updating a global best head pose associated with the set of particles and modifying at least one candidate head pose. The technique further includes modifying a shape of the three-dimensional reference model based on depth data.