Abstract: A server has a processor and a memory storing instructions executed by the processor to maintain an ephemeral gallery of ephemeral messages. An ephemeral message is posted to the ephemeral gallery. The ephemeral message has an associated message duration parameter and a gallery participation parameter. An ephemeral message is removed from the ephemeral gallery in response to the identification of an expired gallery participation parameter.

Abstract: An image system dynamically updates drive sequences in an image system. Drive sequences are image display settings or display driving characteristics with which a display is operated. The image system may determine the drive sequence at least partially based on input from one or more sensors. For example, the image system may include sensors such as an inertial measurement unit, a light sensor, a camera, a temperature sensor, or other sensors from which sensor data may be collected. The image system may analyze the sensor data to calculate drive sequence settings or to select a drive sequence from a number of predetermined drive sequences. Displaying image content on a display includes providing the display with image data and includes operating the display with various drive sequences.

Abstract: Systems and methods herein describe an augmented reality messenger system. The proposed systems and methods generate an augmented reality content item based on input from a first computing device, generate a contextual trigger for the generated augmented reality content, the contextual trigger defining a set of conditions for presenting the generated augmented reality content item on a second computing device, and cause presentation of the generated augmented reality content item on the second computing device based on at least one condition of the set of conditions being satisfied.

Abstract: The technical problem of adding content that originates from a third party application to an augmented reality component maintained by a messaging server system is addressed by configuring the augmented reality component to modify content captured by a camera according to values of one or more attributes and by permitting delivery of said values, from the third party application to the messaging server system, in the payload of a deep link that references the identification of the augmented reality component.

Abstract: Displays and eyewear devices incorporating displays are disclosed. One display includes a light source, a first display region, and a second display region. The first display region includes a first contiguous array of pixels. The first contiguous array of pixels includes a first group of pixels and a second group of pixels interspersed with the first group of pixels. The first group of pixels is adapted to emit light from the light source in only a first wavelength band and the second group of pixels is adapted to emit light from the light source in only a second wavelength band different from the first wavelength band. The second display region consists essentially of a second contiguous array of pixels. The second contiguous array of pixels is adapted to emit light from the light source in a predetermined wavelength band.

Abstract: A server has a processor and a memory storing instructions executed by the processor to maintain an ephemeral gallery of ephemeral messages. In response to a view request received from a client device over a distributed computer network, the message collection is supplied to the requesting device by causing automated sequential display on the client device of the ephemeral messages in the collection. The automated sequential display provides display of the messages one after another in chronological sequence such that the oldest message is displayed first.

Abstract: A method for controlling movement of a drone is disclosed. A spatial vector between a flight-capable drone and a reference object is computed. The spatial vector defines a direction and a distance by which the drone is spaced from the reference object. Flightpath attributes based on the computed vector are determined. The flightpath attributes include one or more of a flight direction, a flight distance, and a flight speed. The flight direction is variable as a function of the direction of the spatial vector. The flight distance is variable as a function of the distance of the spatial vector. The flight speed is variable as a function of the distance of the spatial vector. In an automated operation, movement of the drone is controlled according to the determined flightpath attributes.

Abstract: Aspects of the present disclosure involve a system for presenting AR items. The system receives a video that includes a depiction of a real-world object in a real-world environment. The system generates a three-dimensional (3D) bounding box for the real-world object and stabilizes the 3D bounding box based on one or more sensors of the device. The system determines a position, orientation, and dimensions of the real-world object based on the stabilized 3D bounding box and renders a display of an augmented reality (AR) item within the video based on the position, orientation, and dimensions of the real-world object.

Abstract: Disclosed are methods and systems for ranking content. In one aspect, a method of ranking content for display includes identifying, via hardware processing circuitry, interactions by a single account with content pairs, each of the content in the content pairs included in a plurality of content, aggregating, via the hardware processing circuitry, the identified interactions across a plurality of accounts, associating, via the hardware processing circuitry, probabilities with each content in the plurality of content based on the aggregated interactions, ranking, via the hardware processing circuitry, the plurality of content based on the associated probabilities; and selecting, via the hardware processing circuitry, content ranked above a threshold for display.

Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.

Abstract: System and methods for compressing image-to-image models. Generative Adversarial Networks (GANs) have achieved success in generating high-fidelity images. An image compression system and method adds a novel variant to class-dependent parameters (CLADE), referred to as CLADE-Avg, which recovers the image quality without introducing extra computational cost. An extra layer of average smoothing is performed between the parameter and normalization layers. Compared to CLADE, this image compression system and method smooths abrupt boundaries, and introduces more possible values for the scaling and shift. In addition, the kernel size for the average smoothing can be selected as a hyperparameter, such as a 3×3 kernel size. This method does not introduce extra multiplications but only addition, and thus does not introduce much computational overhead, as the division can be absorbed into the parameters after training.

Abstract: Example systems, devices, media, and methods are described for evaluating movements and physical exercises in augmented reality using the display of an eyewear device. A motion evaluation application implements and controls the capturing of frames of motion data using an inertial measurement unit (IMU) on the eyewear device. The method includes presenting virtual targets on the display, localizing the current eyewear device location based on the captured motion data, and presenting virtual indicators on the display. The virtual targets represent goals or benchmarks for the user to achieve using body postures. The method includes detecting determining whether the eyewear device location represents an intersecting posture relative to the virtual targets, based on the IMU data. The virtual indicators display real-time feedback about user posture or performance relative to the virtual targets.

Abstract: A display-enabled eyewear device has an integrated head sensor that dynamically and continuously measures or detects various cephalic parameters of a wearer's head. The head sensor includes a loop coupler system integrated in a lens-carrying frame to sense proximate ambient RF absorption influenced by head presence, size, and/or distance. Autonomous device management dynamically adjust or cause adjustment of selected device features based on current detected values for the cephalic parameters, which can include wear status, head size, and frame-head spacing.

Abstract: Method of generating customized avatars based on location information includes processor receiving from first client device location information including a location of the first client device. Processor causes a status interface to be displayed on first client device that includes selectable location items corresponding to locations based on the location information. Processor receives a selection from first client device of first selectable location item and causes avatar selection interface to be displayed on first client device that includes versions of first avatar performing actions related to the first selectable location item. Processor receives selection of first selectable version of the first avatar and generates a map interface that includes a map display based on the location information and the first selectable version of the first avatar. Processor causes the map interface to be displayed on at least one of the plurality of client devices. Other embodiments are disclosed.

Abstract: An eyewear device, method for use with an eyewear device, and a non-transient computer readable medium for detecting blood sugar levels are disclosed. The eyewear device has a frame including a first rim configured to support a first lens, a second rim configured to support a second lens, and a bridge connecting the first rim to the second rim. The bridge is configured to receive a nose of a user when the eyewear device is worn by the user. Blood sugar levels are detected by monitoring behavior of a pupil of an eye of the user with a sensor, comparing the monitored behavior with known blood sugar level behaviors, identifying a match responsive to the comparison between the monitored behavior and one of the known blood sugar level behaviors corresponding to a particular blood sugar level, and selecting the particular blood sugar level as a blood sugar level of the user.

Abstract: Aspects of the present disclosure involve systems and methods for performing operations comprising providing a messaging application comprising a feature to a client device, the feature being implemented by operations having alternative complexity levels, wherein a first complexity level represents a first amount of device resources consumed by a first set of operations, and wherein a second complexity level represents a second amount of device resources consumed by a second set of operations; determining that the first configuration rule is satisfied by a first property of the client device; and in response to determining that the first configuration rule is satisfied by the first property of the client device, causing the feature to be implemented on the client device by the first set of operations having the first complexity level that consume a greater amount of device resources than the second set of operations having the second complexity level.

Abstract: A path tracing system in which the traversal task is distributed between one global acceleration structure, which is central in the system, and multiple local acceleration structures, distributed among cells, of high locality and of autonomous processing. Accordingly, the centrality of the critical resource of accelerating structure is reduced, lessening bottlenecks, while improving parallelism.

Abstract: Methods, systems, user interfaces, media, and devices provide a geographically-based graphical user interface (GUI) suited to single-handed operation of a device. The method and system provide for causing display of a GUI including map data displayed in a first view; receiving input comprising at least one input point; determining first and second characteristics of the input; processing, when the first characteristic fulfils a first operational mode criterion, the input according to a first operational mode and causing display of the map data in a second view, the second view being based on the second characteristic of the input; and processing, when the first characteristic of the input fulfils a second operational mode criterion, the input according to a second operational mode, and causing display of the map data in a third view, the third view being based on the second characteristic of the input.

Abstract: Method of generating animation overlays starts with a processor causing a communication interface for a communication session to be displayed at client devices. The processor receives from a first client device an animation sending request and causes an animation sending interface to be displayed in the communication interface of the first client device. The animation sending interface comprises animation overlay icons. Each of the animation overlay icons comprise a first avatar associated with the first user. The processor receives from the first client device a selection of a first animation overlay icon and causes the first animation overlay corresponding to the first animation overlay icon to be displayed as an overlay on the communication interface of each of the plurality of client devices. The first animation overlay is an animation that includes the first avatar. Other embodiments are disclosed.

Abstract: A testing system includes a client library that functions as a proxy for remote procedure calls to allow commands to be issued directly from a test framework including an interface that enables remote procedure call commands to be sent to a device under test from a mobile device and responses from the device under test to be received and forwarded to the mobile device, even where the mobile device and device under test have different operating systems. A client program adapted to run on the device under test sends and receives remote procedure call commands from the device under test to and from a test server that implements the test framework and manages a device state of the device under test. In a pairing test, the remote procedure call commands include commands adapted to emulate a button press for initiating pairing between the mobile device and the device under test.