Abstract: A handheld user device includes a monocular camera to capture a feed of images of a local scene and a processor to select, from the feed, a keyframe and perform, for a first image from the feed, stereo matching using the first image, the keyframe, and a relative pose based on a pose associated with the first image and a pose associated with the keyframe to generate a sparse disparity map representing disparities between the first image and the keyframe. The processor further is to determine a dense depth map from the disparity map using a bilateral solver algorithm, and process a viewfinder image generated from a second image of the feed with occlusion rendering based on the depth map to incorporate one or more virtual objects into the viewfinder image to generate an AR viewfinder image. Further, the processor is to provide the AR viewfinder image for display.

Abstract: An HMD adjusts adjusting depth information based on detected motion of the system. The HMD includes a depth camera that collects depth data for objects in the local environment of the HMD. The HMD further includes an inertial measurement unit (IMU) including non-visual motion sensors such as one or more accelerometers, gyroscopes, and the like. The HMD adjusts the received depth information based on motion data provided by the IMU, thereby improving the accuracy of the depth information, and in turn reducing visual artifacts that can result from inaccuracies in the depth information.

Abstract: An HMD adjusts adjusting depth information based on detected motion of the system. The HMD includes a depth camera that collects depth data for objects in the local environment of the HMD. The HMD further includes an inertial measurement unit (IMU) including non-visual motion sensors such as one or more accelerometers, gyroscopes, and the like. The HMD adjusts the received depth information based on motion data provided by the IMU, thereby improving the accuracy of the depth information, and in turn reducing visual artifacts that can result from inaccuracies in the depth information.

Abstract: A handheld user device includes a monocular camera to capture a feed of images of a local scene and a processor to select, from the feed, a keyframe and perform, for a first image from the feed, stereo matching using the first image, the keyframe, and a relative pose based on a pose associated with the first image and a pose associated with the keyframe to generate a sparse disparity map representing disparities between the first image and the keyframe. The processor further is to determine a dense depth map from the disparity map using a bilateral solver algorithm, and process a viewfinder image generated from a second image of the feed with occlusion rendering based on the depth map to incorporate one or more virtual objects into the viewfinder image to generate an AR viewfinder image. Further, the processor is to provide the AR viewfinder image for display.

Abstract: A method for depth sensor aided estimation of virtual reality environment boundaries includes generating depth data at a depth sensor of an electronic device based on a local environment proximate the electronic device. A set of initial boundary data is estimated based on the depth data, wherein the set of initial boundary data defines an exterior boundary of a virtual bounded floor plan. The virtual bounded floor plan is generated based at least in part on the set of initial boundary data. Additionally, a relative pose of the electronic device within the virtual bounded floor plan is determined and a collision warning is displayed on a display of the electronic device based on the relative pose.

Abstract: A method for depth sensor aided estimation of virtual reality environment boundaries includes generating depth data at a depth sensor of an electronic device based on a local environment proximate the electronic device. A set of initial boundary data is estimated based on the depth data, wherein the set of initial boundary data defines an exterior boundary of a virtual bounded floor plan. The virtual bounded floor plan is generated based at least in part on the set of initial boundary data. Additionally, a relative pose of the electronic device within the virtual bounded floor plan is determined and a collision warning is displayed on a display of the electronic device based on the relative pose.

Abstract: An HMD adjusts adjusting depth information based on detected motion of the system. The HMD includes a depth camera that collects depth data for objects in the local environment of the HMD. The HMD further includes an inertial measurement unit (IMU) including non-visual motion sensors such as one or more accelerometers, gyroscopes, and the like. The HMD adjusts the received depth information based on motion data provided by the IMU, thereby improving the accuracy of the depth information, and in turn reducing visual artifacts that can result from inaccuracies in the depth information.

Abstract: A method for generating virtual reality environment boundaries includes receiving, at a depth sensor of an electronic device, depth data from a local environment proximate the electronic device. Further, a set of outer boundary data is received defines an exterior boundary of a virtual bounded floor plan. A virtual bounded floor plan is generated based at least in part on the set of outer boundary data and the depth data from the local environment. Further, a relative pose of the electronic device within the virtual bounded floor plan is determined and collision warning is displayed on a display of the electronic device based on the relative pose.

Abstract: Methods and systems for calibrating sensors on a computing device are described herein. In an example implementation, a computing device may perform a method to calibrate one or more sensors, which may include receiving an indication that a sensor has been calibrated. The computing device may further receive independent observations of a motion of a device from the calibrated sensor and a potentially non-calibrated sensor. The device may determine as independent estimation of motion based on the movement of the device corresponding to the outputs of the respective sensors. Based on whether or not the estimation of motion as provided by the potentially non-calibrated sensor is within a threshold variance of the estimation of motion as provided by the calibrated sensor, the computing device may provide instructions to adjust parameters of the non-calibrated sensor.

Abstract: Methods and systems for calibrating sensors on a computing device are described herein. In an example implementation, a computing device may perform a method to calibrate one or more sensors, which may include receiving an indication that a sensor has been calibrated. The computing device may further receive independent observations of a motion of a device from the calibrated sensor and a potentially non-calibrated sensor. The device may determine as independent estimation of motion based on the movement of the device corresponding to the outputs of the respective sensors. Based on whether or not the estimation of motion as provided by the potentially non-calibrated sensor is within a threshold variance of the estimation of motion as provided by the calibrated sensor, the computing device may provide instructions to adjust parameters of the non-calibrated sensor.

Abstract: Methods and systems for map generation are described. A computing device may receive outputs from a plurality of sensors at a position of the device in an environment, which may include data corresponding to visual features of the environment at the first position. Based on correspondence in the outputs from the plurality of sensors, the computing device may generate a map of the environment comprising sparse mapping data, and the sparse mapping data comprises the data corresponding to the visual features. The device may receive additional outputs at other positions of the device in the environment and may modify the map based on the additional outputs. In addition, the device may modify the map based on receiving dense mapping information from sensors, which may include data corresponding to objects in the environment in a manner such that represents a structure of the object in the environment.