Abstract: Systems and methods for localization for mobile devices are described. Some implementations may include accessing motion data captured using one or more motion sensors; determining, based on the motion data, a coarse localization, wherein the coarse localization includes a first estimate of position; obtaining one or more feature point maps, wherein the feature point maps are associated with a position of the coarse localization; accessing images captured using one or more image sensors; determining, based on the images, a fine localization pose by localizing into a feature point map of the one or more feature point maps, wherein the fine localization pose includes a second estimate of position and an estimate of orientation; generating, based on the fine localization pose, a virtual object image including a view of a virtual object; and displaying the virtual object image.

Abstract: Various implementations disclosed herein include devices, systems, and methods that enable a device to provide a view of virtual elements and a physical environment where the presentation of the virtual elements is based on positioning relative to the physical environment. In one example, a device is configured to detect a change in positioning of a virtual element, for example, when a virtual element is added, moved, or the physical environment around the virtual element is changed. The location of the virtual element in the physical environment is used to detect an attribute of the physical environment upon which the presentation of the virtual element depends. Thus, the device is further configured to detect an attribute (e.g., surface, table, mid-air, etc.) of the physical environment based on the placement of the virtual element and present the virtual element based on the detected attribute.

Abstract: Systems and techniques for generating an artificial terrain map can select a plurality of component terrains for each of several terrain types. Values of a selection noise map ranging between a lower bound and an upper bound can be computed on a tile-by-tile basis. One or more noise bands within the range of selection-noise-map values can correspond to each terrain type. The noise map can be sampled on a tile-by-tile basis to determine a tile value for each tile. Each respective tile can be assigned to the noise band in which the tile value falls. A terrain value can be assigned to each respective tile in the selection noise map based on the noise band assigned to the respective tile. Generated maps in machine-readable form can be converted to a human-perceivable form, and/or to a modulated signal form conveyed over a communication connection.

Abstract: A method includes obtaining first pass-through image data characterized by a first pose. The method includes obtaining respective pixel characterization vectors for pixels in the first pass-through image data. The method includes identifying a feature of an object within the first pass-through image data in accordance with a determination that pixel characterization vectors for the feature satisfy a feature confidence threshold. The method includes displaying the first pass-through image data and an AR display marker that corresponds to the feature. The method includes obtaining second pass-through image data characterized by a second pose. The method includes transforming the AR display marker to a position associated with the second pose in order to track the feature. The method includes displaying the second pass-through image data and maintaining display of the AR display marker that corresponds to the feature of the object based on the transformation.

Abstract: Systems and methods for generating a video of an emoji that has been puppeted using inputs from image, depth, and audio. The inputs can capture facial expressions of a user, eye, eyebrow, mouth, and head movements. A pose, held by the user, can be detected that can be used to generate supplemental animation. The emoji can further be animated using physical properties associated with the emoji and captured movements. An emoji of a dog can have its ears move in response to an up-and-down movement, or a shaking of the head. The video can be sent in a message to one or more recipients. A sending device can render the puppeted video in accordance with hardware and software capabilities of a recipient's computer device.

Abstract: Systems and methods for generating a video of an emoji that has been puppeted using inputs from image, depth, and audio. The inputs can capture facial expressions of a user, eye, eyebrow, mouth, and head movements. A pose, held by the user, can be detected that can be used to generate supplemental animation. The emoji can further be animated using physical properties associated with the emoji and captured movements. An emoji of a dog can have its ears move in response to an up-and-down movement, or a shaking of the head. The video can be sent in a message to one or more recipients. A sending device can render the puppeted video in accordance with hardware and software capabilities of a recipient's computer device.

Abstract: Systems and methods for generating a video of an emoji that has been puppeted using inputs from image, depth, and audio. The inputs can capture facial expressions of a user, eye, eyebrow, mouth, and head movements. A pose, held by the user, can be detected that can be used to generate supplemental animation. The emoji can further be animated using physical properties associated with the emoji and captured movements. An emoji of a dog can have its ears move in response to an up-and-down movement, or a shaking of the head. The video can be sent in a message to one or more recipients. A sending device can render the puppeted video in accordance with hardware and software capabilities of a recipient's computer device.

Abstract: Techniques to automatically generate a navigation graph for a given environment and agent are disclosed. The environment may include an arbitrary number of polygonal obstacles arbitrarily arranged, concave or convex, static or dynamic. The disclosed operation extrudes (in a specified manner) the vertex of each obstacle. The extruded vertices comprise the navigation graph's nodes. Each object's extruded vertices may be joined to form a corresponding extruded object. Paths may then be identified by attempting to connect every extruded vertex with every other extruded vertex. Those paths intersecting any of the extruded objects are rejected as possible paths. In some embodiments, paths that are oriented in approximately the same direction having approximately the same length may be removed as being redundant.

Abstract: A method may include receiving a communication from a device at an artificial intelligence controller including state information for a software application component running on the device, the state information including information corresponding to at least one potential state change available to the software application component, and metrics associated with at least one end condition, interpreting the state information using the artificial intelligence controller, and selecting an artificial intelligence algorithm from a plurality of artificial intelligence algorithms for use by the software application component based on the interpreted state information; and transmitting, to the device, an artificial intelligence algorithm communication, the artificial intelligence algorithm communication indicating the selected artificial intelligence algorithm for use in the software application component on the device.

Abstract: A method may include receiving, at an artificial intelligence cloud service, a plurality of artificial intelligence feedback communications from a plurality of devices, wherein each artificial intelligence feedback communication of the plurality of artificial intelligence feedback communications includes data generated by software application components running on respective ones of the plurality of devices, the software application components including respective current artificial intelligence models, deriving, from the data included with each artificial intelligence feedback communication, an associated artificial intelligence model update for each of the respective current artificial intelligence models on the plurality of devices, and transmitting, to the plurality of devices, a plurality of artificial intelligence model update communications, wherein each artificial intelligence model update communication of the plurality of artificial intelligence model update communications includes the derived associ

Abstract: Systems and techniques for generating an artificial terrain map can select a plurality of component terrains for each of several terrain types. Values of a selection noise map ranging between a lower bound and an upper bound can be computed on a tile-by-tile basis. One or more noise bands within the range of selection-noise-map values can correspond to each terrain type. The noise map can be sampled on a tile-by-tile basis to determine a tile value for each tile. Each respective tile can be assigned to the noise band in which the tile value falls. A terrain value can be assigned to each respective tile in the selection noise map based on the noise band assigned to the respective tile. Generated maps in machine-readable form can be converted to a human-perceivable form, and/or to a modulated signal form conveyed over a communication connection.

Abstract: Systems, methods, and computer readable media to improve the operation of graphics systems are described. In general, collision avoidance techniques are disclosed that operate even when the agent lacks a priori knowledge of its environment and is, further, agnostic as to whether the environment is two-dimensional (2D) or three-dimensional (3D), whether the obstacles are convex or concave, or whether the obstacles are moving or stationary. More particularly, techniques disclosed herein use simple geometry to identify which edges of which obstacles an agent is most likely to collide. With this known, the direction of an avoidance force is also known. The magnitude of the force may be fixed, based on the agent's maximum acceleration, and modulated by weighting agents.

Abstract: Systems, methods, and computer-readable media for enabling efficient control of a media application at a media electronic device by a user electronic device are provided.

Abstract: Systems, methods, and computer readable media to improve the operation of graphics systems are described. In general, collision avoidance techniques are disclosed that operate even when the agent lacks a priori knowledge of its environment and is, further, agnostic as to whether the environment is two-dimensional (2D) or three-dimensional (3D), whether the obstacles are convex or concave, or whether the obstacles are moving or stationary. More particularly, techniques disclosed herein use simple geometry to identify which edges of which obstacles an agent is most likely to collide. With this known, the direction of an avoidance force is also known.

Abstract: Techniques to automatically generate a navigation graph for a given environment and agent are disclosed. The environment may include an arbitrary number of polygonal obstacles arbitrarily arranged, concave or convex, static or dynamic. The disclosed operation extrudes (in a specified manner) the vertex of each obstacle. The extruded vertices comprise the navigation graph's nodes. Each object's extruded vertices may be joined to form a corresponding extruded object. Paths may then be identified by attempting to connect every extruded vertex with every other extruded vertex. Those paths intersecting any of the extruded objects are rejected as possible paths. In some embodiments, paths that are oriented in approximately the same direction having approximately the same length may be removed as being redundant.