Abstract: In one embodiment, a method includes, by an electromagnetic device, emitting optical radiation on one or more objects disposed inside an interior of the electronic device, where the optical radiation is emitted by one or more radiation sources, capturing a set of 2D images of the one or more objects illuminated by the optical radiation, where variation of illumination or of an imaging process permits the set of 2D images to be combined into a representation of the one or more objects, determining whether the set of images comprises a representation of the one or more objects as imaged, in response to determining that the set of images comprises a representation of the one or more objects as imaged, generating a three-dimensional (3D) spectral data cube of the one or more first objects based on spectral information of the first set of images, and storing the 3D spectral data cube for processing by the electronic device.

Abstract: An apparatus includes a display device having a lenticular layer. The lenticular layer includes (i) a first side, (ii) a second side opposite the first side, and (iii) particles in a fluid medium between the first and second sides of the lenticular layer. The second side of the lenticular layer includes lens elements forming a lenticular array. The particles of the lenticular layer are configured to move within the fluid medium such that (i) the lens elements are filled with the particles in a first mode or (ii) the lens elements are filled with the fluid medium in a second mode. The display device is configured to operate as a directional display in one of the first and second modes and as a single display in another of the first and second modes.

Abstract: In one embodiment, a method includes, by an electromagnetic device, emitting optical radiation on one or more objects disposed inside an interior of the electronic device, where the optical radiation is emitted by one or more radiation sources, capturing a set of 2D images of the one or more objects illuminated by the optical radiation, where variation of illumination or of an imaging process permits the set of 2D images to be combined into a representation of the one or more objects, determining whether the set of images comprises a representation of the one or more objects as imaged, in response to determining that the set of images comprises a representation of the one or more objects as imaged, generating a three-dimensional (3D) spectral data cube of the one or more first objects based on spectral information of the first set of images, and storing the 3D spectral data cube for processing by the electronic device.

Abstract: A method for controlling content rendering by a multi-view, directionally dependent display includes defining a first display as a first pixel of a pixelated array of the multi-view display, the first display associated with a first viewing angle relative to a first axis; and defining a second display as a second pixel of the pixelated array, the second display. The method includes controlling chromatic properties of the first pixel by applying a filter based on a rendering of first content to be displayed. The method also includes controlling chromatic properties of the second pixel by applying a filter based on a rendering of second content to be displayed; and controlling points of incidence of light from the first and second pixel relative to an optical multiplexer thereby changing the directionality of the multi-view, directionally dependent display.

Abstract: In one embodiment, a method includes, by an electromagnetic device, accessing multiple previously recorded heating maps corresponding to a load disposed inside a cavity, where each heating map indicates a temperature profile change of the load as a function of one or more control parameter configurations, accessing a target temperature profile of the load, measuring a current temperature profile of the load, calculating a difference in temperature profiles between the current temperature profile of the load and the target temperature profile of the load, determining a first sequence of control parameter configurations to heat the load, wherein the first sequence is optimized to yield a temperature rise that achieves the target temperature profile of the load, emitting electromagnetic radiation into the cavity based on the first sequence of control parameter configurations.

Abstract: In one embodiment, a method includes by an electronic device: receiving sensor data indicative of a touch input from one or more sensors of a touch panel of the electronic device, where the touch input occurs at a detected touch location of the touch panel, accessing a baseline of signal data corresponding to the touch panel, calculating a delta change based on the baseline of the signal data and the sensor data, determining a touch state corresponding to the touch input based on a comparison of the delta change to a plurality of touch threshold levels, selecting a touch location prediction method from a plurality of touch location prediction methods based on the touch state, and determining a predicted touch location of the touch input based on the touch location prediction method and the sensor data.

Abstract: In one embodiment, a method of training a machine-learning model for modifying a facial illumination in an image includes accessing an initial image including a human face having an initial illumination and determining one or more illumination priors for the initial image. The method includes providing the initial image and the one or more illumination priors to the machine-learning model; receiving, from the machine-learning model, a set of correction operators identifying a modified illumination for the human face; creating, based at least on the set of correction operators and the initial image, a modified image having the modified illumination; creating, based on the modified image, a reconstructed initial image including the human face having a reconstructed illumination; and adjusting one or more parameters of the machine-learning model by minimizing a loss function based on a difference between the initial and the reconstructed initial images in their respective illumination.

Abstract: In one embodiment, a method includes by an electronic device: receiving sensor data indicative of a touch input from sensors of a human interface-device (HID) of the electronic device, where the touch input occurs at a set of actual coordinates with respect to the HID, and where the sensor data indicates the touch input occurs at a set of detected coordinates with respect to the HID, determining a context associated with the touch input, determining, by one or more generative models, context-dependent statistics to apply a delta change to the set of detected coordinates, where the context-dependent statistics are based on the context associated with the touch input, and where the one or more generative models comprises one or more system parameters and one or more latent parameters, and determining a set of time-lapsed predicted coordinates of the touch input with respect to the HID based on the delta change.

Abstract: In one embodiment, a method includes, by an electromagnetic device, generating an initial map of a temperature profile of a load disposed inside a cavity, emitting electromagnetic radiation into the cavity based on initial control parameter configurations, where a change in temperature of the load during the emission is measured by one or more sensors, generating updated maps of electromagnetic energy absorbed by the load based on the measured change in temperature of the load, where the updated maps comprise an indication of a spatial heating rate within the load, determining a sufficient number of the updated maps of electromagnetic energy absorbed by the load disposed inside the cavity have been measured, and, in response to determining that a sufficient number of the one or more updated maps of electromagnetic energy have been measured, storing the updated maps of electromagnetic energy absorbed by the load.

Abstract: In one embodiment, a method includes by a robotic system: sending, by an automatic tuning controller, driving commands to actuators of the robotic system, performing, for each of the actuators, one or more measurements of an actual pose of the respective actuator in response to the driving commands, generating, for each of the actuators, one or more configuration parameters for the respective actuator based on the one or more measurements, and storing the configuration parameters for the actuators in a data store of the robotic system.

Abstract: In one embodiment, a method includes accessing real-time content captured by a first user's client device, where the real-time content is captured at a first high quality and is one of a plurality of content frames in a real-time stream of content. The method includes downgrading the quality of the real-time content to a second lower quality for transmission to a second user and transmitting the downgraded content to the second user. The method includes determining, based on a request made by the second user, an area of interest of a subsequent real-time image, where the subsequent real-time image is at the first high quality, modifying the subsequent real-time image to focus on the area of interest, where the modified subsequent real-time image is at the first high quality, and downgrading and transmitting the modified subsequent real-time image for to the second user.

Abstract: Image de-skewing can include acquiring pixel coordinates of an image captured by a camera adjoining an electronic display device. The pixel coordinates can be mapped to de-skewing coordinates using a predetermined de-skewing transformer that maps the pixel coordinates to de-skewing coordinates. A de-skewed image can be generated based on the de-skewing coordinates such that the de-skewed image is perpendicular to a principal axis extending from a predetermined location of an apparent camera on the electronic display device.

Abstract: In one embodiment, a method includes by a robotic system: accessing a trajectory plan to be executed by the robotic system, where the trajectory plan includes desired poses at specified times, respectively, for each actuator of the robotic system, executing the trajectory plan for each actuator of the robotic system; monitoring, in real-time for each actuator during execution of the trajectory plan, an actual pose of the respective actuator, determining, based on the monitoring of the actuators, that one or more of the actuators is lagging, where the actual pose of each lagging actuator deviates from the desired pose by more than an error threshold, and adjusting, in real-time responsive to determining that one or more of the actuators is lagging, one or more of the desired poses at one or more specified times, respectively, of the trajectory plan.

Abstract: A system and method include generating environment data from skylight sensor data. The environment data includes a value of a geospatially dependent parameter associated with light received from a predetermined celestial light source. At least two of a compass direction of the predetermined celestial light source when the skylight sensor data was received, a time at which the skylight sensor data was received, or a geospatial coordinate at which the skylight sensor data was collected are received. At least one of the compass direction of the predetermined celestial light source when the skylight sensor data was received, the time at which the skylight sensor data was received, or the geospatial coordinate at which the skylight sensor data was collected is determined, at least in part, from the environment data.

Abstract: A method by an electromagnetic device includes determining a pattern of electromagnetic energy absorbed by a load disposed inside a cavity into which electromagnetic radiation is directed and generating one or more maps of the pattern of electromagnetic energy absorbed by the load. The one or more maps comprises an indication of a distribution of heating within the load. The method further includes determining, based on the one or more maps, a plurality of sequences of operating parameter combinations configured so as to heat the load via absorption of the electromagnetic radiation in accordance with a target temperature profile with respect to the load. The method thus includes emitting electromagnetic radiation into the cavity based on the plurality of sequences of operating parameter combinations to achieve the target temperature profile with respect to the load.

Abstract: An apparatus includes a display device having a lenticular layer. The lenticular layer includes (i) a first side, (ii) a second side opposite the first side, and (iii) particles in a fluid medium between the first and second sides of the lenticular layer. The second side of the lenticular layer includes lens elements forming a lenticular array. The particles of the lenticular layer are configured to move within the fluid medium such that (i) the lens elements are filled with the particles in a first mode or (ii) the lens elements are filled with the fluid medium in a second mode. The display device is configured to operate as a directional display in one of the first and second modes and as a single display in another of the first and second modes.

Abstract: In one embodiment, a method includes by a robotic system: sending, by an automatic tuning controller, driving commands to actuators of the robotic system, performing, for each of the actuators, one or more measurements of an actual pose of the respective actuator in response to the driving commands, generating, for each of the actuators, one or more configuration parameters for the respective actuator based on the one or more measurements, and storing the configuration parameters for the actuators in a data store of the robotic system.

Abstract: In one embodiment, a method includes by a robotic system: accessing a trajectory plan to be executed by the robotic system, where the trajectory plan includes desired poses at specified times, respectively, for each actuator of the robotic system, executing the trajectory plan for each actuator of the robotic system; monitoring, in real-time for each actuator during execution of the trajectory plan, an actual pose of the respective actuator, determining, based on the monitoring of the actuators, that one or more of the actuators is lagging, where the actual pose of each lagging actuator deviates from the desired pose by more than an error threshold, and adjusting, in real-time responsive to determining that one or more of the actuators is lagging, one or more of the desired poses at one or more specified times, respectively, of the trajectory plan.

Abstract: An apparatus includes a backlight, a color filter disposed in front of the backlight along a viewing direction, wherein the color filter includes a plurality of pixels repeating at a first spacing along a first axis. The apparatus further includes a lenticular layer disposed in front of the backlight, the lenticular layer including a section of material having a first index of refraction, a first, substantially flat side, and a second side defining a lenticularly patterned cross section along the first axis, the lenticularly patterned cross section including lens elements repeating at a second spacing and directing light originating from the backlight in two or more directions.

Abstract: The present disclosure describes a system and method for a marker-based augmented reality system. The method includes acquiring image data from a camera, analyzing the image data to identify at least one marker, the at least one marker being associated with a physical location in a real-world environment, determining information represented via the at least one marker, the information represented via the at least one marker including at least one of content data, metadata, or server data, generating content based on the at least one of the content data, the metadata, or the server data, and presenting, via a display, the content overlaying a displayed representation of the real-world environment, the content being presented at one or more locations in the displayed representation of the real-world environment relative to the physical location associated with the at least one marker.