Abstract: A processor accesses a depth map and a first image of a scene generated using one or more sensors of an artificial reality device. The processor generates, based on the first image, segmentation masks respectively associated with a plurality of object types. The segmentation masks segment the depth map into a plurality of segmented depth maps respectively associated with the object types. The processor generates meshes using, respectively, the segmented depth maps. For each eye of the user, the processor captures a second image and generates, based on the second image, segmentation information. The processor warps the plurality of meshes to generate warped meshes for the eye, and then generates an eye-specific mesh for the eye by compositing the warped meshes according to the segmentation information. The processor renders an output image for the eye using the second image and the eye-specific mesh.

Abstract: In one embodiment, a computing system may receive sensor data from an image sensor having a pixel array including color pixel sensors and panchromatic pixel sensors in a first pattern. Each of the color pixel sensors is associated with one of several color channels. The computing system may generate, based on the sensor data, a filtered monochrome image including monochrome values corresponding to the pixel array of the image sensor. The computing system may generate a filtered color image having a second pattern of color channels. A first pixel of a particular color channel at a first pixel location in the filtered color image is determined based on the monochrome value corresponding to the first pixel location in the filtered monochrome image, the sensor data measured by a color pixel sensor at a second pixel location, and the monochrome value at the second pixel location in the filtered monochrome image.

Abstract: Embodiments of the present disclosure support a head-mounted display (HMD) wirelessly coupled to a console. The HMD includes a positional tracking system, a beam controller and a transceiver. The positional tracking system tracks position of the HMD and generates positional information describing the tracked position of the HMD. The transceiver communicates with a console via a wireless channel, in accordance with communication instructions, the communication instructions causing the transceiver to communicate over one directional beam of a plurality of directional beams. The beam controller determines a change in the positional information. Based on the change to the positional information, the beam controller determines a directional beam of the plurality of directional beams. The beam controller further generates the communication instructions identifying the determined directional beam, and provides the communication instructions to the transceiver.

Abstract: A calibration system includes a grid assembly, a platform, and a controller. The grid assembly includes at least one planar grid. The platform couples to a device under test (DUT) and move the DUT to a plurality of test positions in accordance with a motion sequence. Each test position is reached by a rotation about at most two different axes, and as the DUT moves through the motion sequence, at least one camera on the DUT captures image information describing portions of the grid assembly and an inertial measurement unit (IMU) on the DUT captures IMU information. The controller determines calibration information for the at least one camera on the DUT and for the IMU based in part on a parameterized model of the motion sequence of the DUT, the captured image information, and the captured IMU information.

Abstract: The disclosed computer-implemented method for offloading image-based tracking operations from a general processing unit to a hardware accelerator unit may include (1) sending imaging data from an imaging device to a hardware accelerator unit, and (2) directing the hardware accelerator unit to generate a multi-scale representation of the imaging data sent from the imaging device, (3) preparing a set of input data for a set of image-based tracking operations, and (4) directing the hardware accelerator unit to execute the set of image-based tracking operations using the generated multi-scale representation of the imaging data and the prepared set of input data. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An artificial reality system is described includes a hand-held controller tracking sub-system having two components, a Field-of-View (FOV) tracker and a non-FOV tracker that applies specialized motion models when one or more of controllers are not trackable within the field of view. In particular, under typical operating conditions, the FOV tracker receives state data for a Head Mounted Display (HMD) and controller state data (velocity, acceleration etc.) of a controller to compute estimated poses for the controller. If the controller is trackable (e.g., within the field of view and not occluded), then the pose as computed by the FOV tracker is used and the non-FOV tracker is bypassed. If the controller is not trackable within the field of view and the controller state data meets activation conditions for one or more corner tracking cases, then the non-FOV tracker applies one or more of specialized motion models to compute a controller pose for the controller.

Abstract: An artificial reality system is described includes a hand-held controller tracking sub-system having two components, a Field-of-View (FOV) tracker and a non-FOV tracker that applies specialized motion models when one or more of controllers are not trackable within the field of view. In particular, under typical operating conditions, the FOV tracker receives state data for a Head Mounted Display (HMD) and controller state data (velocity, acceleration etc.) of a controller to compute estimated poses for the controller. If the controller is trackable (e.g., within the field of view and not occluded), then the pose as computed by the FOV tracker is used and the non-FOV tracker is bypassed. If the controller is not trackable within the field of view and the controller state data meets activation conditions for one or more corner tracking cases, then the non-FOV tracker applies one or more of specialized motion models to compute a controller pose for the controller.

Abstract: A head-mounted display (HMD) is configured to capture images and/or video of a local area. The HMD includes an imaging assembly and a controller. The imaging assembly includes a plurality of cameras positioned at different locations on the HMD and oriented to capture images of different portions of a local area surrounding the HMD. The controller generates imaging instructions for each camera using image information. The imaging instructions cause respective midpoints of exposure times for each camera to occur at a same time value for each of the captured images. The cameras capture images of the local area in accordance with the imaging instructions. The controller determines a location of the HMD in the local area using the captured images and updates a model that represents a mapping function of the depth and exposure settings of the local area.

Abstract: A virtual reality (VR) system tracks the location and position of a controller using image sensors on a headset and a controller. The headset and controller provide a first and second view of a user's environment. Using its camera, the headset generates a map of the environment and identifies its location within it. Based headset's location, the VR system generates a simulated world of the environment and displays it to the user. The headset also estimates the location of the controller. Based on the estimated location, the headset sends a portion of the map to the controller. The controller determines its pose using the portion of the map, the image sensors, and additional sensors. The controller sends its pose and an updated portion of the map to the headset. Based on the controller's pose and updated portion of the map, the VR system modifies the content displayed to the user.

Abstract: Embodiments of the present disclosure support a head-mounted display (HMD) wirelessly coupled to a console. The HMD includes a positional tracking system, a beam controller and a transceiver. The positional tracking system tracks position of the HMD and generates positional information describing the tracked position of the HMD. The transceiver communicates with a console via a wireless channel, in accordance with communication instructions, the communication instructions causing the transceiver to communicate over one directional beam of a plurality of directional beams. The beam controller determines a change in the positional information. Based on the change to the positional information, the beam controller determines a directional beam of the plurality of directional beams. The beam controller further generates the communication instructions identifying the determined directional beam, and provides the communication instructions to the transceiver.

Abstract: An apparatus for wearable head-mounted displays may include a head-mounted display that includes (i) four lateral cameras, including (a) a camera that is mounted on a right side of the head-mounted display, (b) a camera that is mounted on a left side of the head-mounted display, (c) a camera that is mounted on a front of the head-mounted display and is right of a center of the front of the head-mounted display, and (e) a camera that is mounted on the front of the head-mounted display and is left of a center of the front of the head-mounted display, (ii) one central camera that is mounted on the front of the head-mounted display, and (iii) at least one display surface that displays visual data to a wearer of the head-mounted display. Various other apparatuses, systems, and methods are also disclosed.

Abstract: Embodiments of the present disclosure support a head-mounted display (HMD) wirelessly coupled to a console. The HMD includes a positional tracking system, a beam controller and a transceiver. The positional tracking system tracks position of the HMD and generates positional information describing the tracked position of the HMD. The transceiver communicates with a console via a wireless channel, in accordance with communication instructions, the communication instructions causing the transceiver to communicate over one directional beam of a plurality of directional beams. The beam controller determines a change in the positional information. Based on the change to the positional information, the beam controller determines a directional beam of the plurality of directional beams. The beam controller further generates the communication instructions identifying the determined directional beam, and provides the communication instructions to the transceiver.

Abstract: A head-mounted display (HMD) is configured to capture images and/or video of a local area. The HMD includes an imaging assembly and a controller. The imaging assembly includes a plurality of cameras positioned at different locations on the HMD and oriented to capture images of different portions of a local area surrounding the HMD. The controller generates imaging instructions for each camera using image information. The imaging instructions cause respective midpoints of exposure times for each camera to occur at a same time value for each of the captured images. The cameras capture images of the local area in accordance with the imaging instructions. The controller determines a location of the HMD in the local area using the captured images and updates a model that represents a mapping function of the depth and exposure settings of the local area.

Abstract: The disclosed computer-implemented method for offloading image-based tracking operations from a general processing unit to a hardware accelerator unit may include (1) sending imaging data from an imaging device to a hardware accelerator unit, and (2) directing the hardware accelerator unit to generate a multi-scale representation of the imaging data sent from the imaging device, (3) preparing a set of input data for a set of image-based tracking operations, and (4) directing the hardware accelerator unit to execute the set of image-based tracking operations using the generated multi-scale representation of the imaging data and the prepared set of input data. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A calibration system is configured to determine calibration information of a head-mounted display (HMD). The calibration system comprises a first, second, and third planar grid, a movable platform, and a calibration controller. Each planar grid includes a plurality of fiducial markers that are displayed in accordance with a display pattern. The HMD is coupled to the movable platform, which moves the HMD before the planar grids as a plurality of cameras on the HMD captures images of the planar grids with fiducial markers. The calibration controller controls a motion sequence of the movable platform and determines calibration information for each of the cameras on the HMD and calibration information for an inertial measurement unit (IMU) within the HMD. The calibration information is based in part on a parameterized model of the motion sequence of the HMD.

Abstract: A head-mounted display (HMD) is configured to capture images and/or video of a local area. The HMD includes an imaging assembly and a controller. The imaging assembly includes a plurality of cameras positioned at different locations on the HMD and oriented to capture images of different portions of a local area surrounding the HMD. The controller generates imaging instructions for each camera using image information. The imaging instructions cause respective midpoints of exposure times for each camera to occur at a same time value for each of the captured images. The cameras capture images of the local area in accordance with the imaging instructions. The controller determines a location of the HMD in the local area using the captured images and updates a model that represents a mapping function of the depth and exposure settings of the local area.

Abstract: Embodiments of the present disclosure support a head-mounted display (HMD) wirelessly coupled to a console. The HMD includes a positional tracking system, a beam controller and a transceiver. The positional tracking system tracks position of the HMD and generates positional information describing the tracked position of the HMD. The transceiver communicates with a console via a wireless channel, in accordance with communication instructions, the communication instructions causing the transceiver to communicate over one directional beam of a plurality of directional beams. The beam controller determines a change in the positional information. Based on the change to the positional information, the beam controller determines a directional beam of the plurality of directional beams. The beam controller further generates the communication instructions identifying the determined directional beam, and provides the communication instructions to the transceiver.

Abstract: A head-mounted display (HMD) is configured to capture images and/or video of a local area. The HMD includes an imaging assembly and a controller. The imaging assembly includes a plurality of cameras positioned at different locations on the HMD and oriented to capture images of different portions of a local area surrounding the HMD. The controller generates imaging instructions for each camera using image information. The imaging instructions cause respective midpoints of exposure times for each camera to occur at a same time value for each of the captured images. The cameras capture images of the local area in accordance with the imaging instructions. The controller determines a location of the HMD in the local area using the captured images and updates a model that represents a mapping function of the depth and exposure settings of the local area.

Abstract: A calibration system is configured to determine calibration information of a head-mounted display (HMD). The calibration system comprises a first, second, and third planar grid, a movable platform, and a calibration controller. Each planar grid includes a plurality of fiducial markers that are displayed in accordance with a display pattern. The HMD is coupled to the movable platform, which moves the HMD before the planar grids as a plurality of cameras on the HMD captures images of the planar grids with fiducial markers. The calibration controller controls a motion sequence of the movable platform and determines calibration information for each of the cameras on the HMD and calibration information for an inertial measurement unit (IMU) within the HMD. The calibration information is based in part on a parameterized model of the motion sequence of the HMD.

Abstract: A virtual reality (VR) system tracks the position of a controller. The VR system includes an image tracking system comprising of a number of fixed cameras, and a headset worn by the user that includes an imaging device to capture images of a controller operated by the user. The controller includes a set of features disposed on the surface of the controller. The image tracking system provides a first view of the controller. The imaging device mounted on the headset provides a second view of the controller. Each view of the controller (i.e., from the headset and from the image tracking system) provides a distinct set of features observed on the controller. The first and second sets of features are identified from the captured images and a pose of the controller is determined using the first set of features and the second set of features.