Snap Inc.

Daqri, LLC

Facebook Technologies, LLC

Meta Platforms Technologies, LLC

Kai Zhou

Daniel Wagner

Matthias Kalkgruber

Clemens Birklbauer

Daniel Wolf

Jeroen Diederik Hol

Qi Qi

Dunxu Hu

Erick Mendez Mendez

Georg Halmetschlager-Funek

Dominik Schnitzer

Yubin Xi

Erick Mendez

Adrian Schoisengeier

Brian Mullins

Avihay Assouline

Riza Alp Guler

Jennica Pounds

Bernhard Jung

Iason Kokkinos

Branislav Micusik

Lucas Kazansky

Roy Lawrence Ashok Inigo

Frank Chester Irving, Jr

Kiyoung Kim

Himmy Tam

Thomas Muttenthaler

Tiago Miguel Pereira Torres

Kenneth Au

Zsolt Robotka

Xiao Li

Jonathan Trevor Freeman

Márton Gergely Kajtár

Laura Rosalia Luidolt

Xinrong Wei

An XR system is provided that enhances user interaction within extended reality environments through precise hand scale estimation. The XR system is configured to capture tracking data of a user's hand as the user interacts with a mobile device. Concurrently, the XR system captures pose data of itself and uses the tracking data and the pose data to determine a reference line segment. This segment aids in calculating three-dimensional distances between node pairs of the user's hand. By employing these measurements, the XR system effectively calculates a hand scale factor that is used for accurately integrating the user's hands into an XR user interface.

Hand scale factor estimation from mobile interactions

A method for programming a robotic system by demonstration is described. In one aspect, the method includes displaying a first virtual object in a display of an augmented reality (AR) device, the first virtual object corresponding to a first physical object in a physical environment of the AR device, tracking, using the AR device, a manipulation of the first virtual object by a user of the AR device, identifying an initial state and a final state of the first virtual object based on the tracking, the initial state corresponding to an initial pose of the first virtual object, the final state corresponding to a final pose of the first virtual object, and programming by demonstration a robotic system using the tracking of the manipulation of the first virtual object, the first initial state of the first virtual object, and the final state of the first virtual object.

Robotic learning of assembly tasks using augmented reality

Examples describe adaptive image processing for an augmented reality (AR) device. An input image is captured by a camera of the AR device, and a region of interest of the input image is determined. The region of interest is associated with an object that is being tracked using an object tracking system. A crop-and-scale order of an image processing operation directed at the region of interest is determined for the input image. One or more object tracking parameters may be used to determine the crop-and-scale order. The crop-and-scale order is dynamically adjustable between a first order and a second order. An output image is generated from the input image by performing the image processing operation according to the determined crop-and-scale order for the particular input image. The output image can be accessed by the object tracking system to track the object.

Adaptive image processing for augmented reality device

An eyewear device including a sensor used to measure deformation of an eyewear frame to estimate an inter-pupillary distance (IPD) of an eyewear user. The sensor is used to determine head breadth (HB) of the user and to estimate the IPD of the user. A processor displays an image on a display of the eyewear as a function of the estimated IPD to improve virtual object rendering for an improved augmented reality (AR) viewing experience while reducing vergence accommodation mismatch (VAM). User profile data, such as age and gender, can be used to generate a more accurate estimated IPD of the user.

Eyewear with inter-pupillary distance estimation

A content creation system for extended Reality (XR) systems. The content creation system receives motion data of an XR device and generates trajectory data of a trajectory within a 3D environment model of a real-world scene based on the motion data where the trajectory simulates the motion of the XR device within the real-world scene. The content creation system receives user interaction event data and generates simulated sensor data based on the trajectory data, the 3D environment model, and the user interaction event data. The content creation system generates simulated tracking data based on the simulated sensor data and determines simulated power consumption data and thermal condition data based on operation of the computer vision component while generating the simulated tracking data. The content creation system generates a display from a user's perspective of the 3D environment model along with the simulated power consumption and thermal data.

Content creation platform for XR devices

Methods and systems are disclosed for transferring garments from a real-world object to a virtual object. The system receives, by a client device, an image that includes a depiction of a real-world object having a fashion item in a real-world environment. The system accesses a three-dimensional (3D) avatar model of a human and generates a graphic item corresponding to the fashion item being worn by the real-world object depicted in the image. The system modifies the 3D avatar model of the human based on the graphic item and presents the 3D avatar model that has been modified based on the graphic item within a view of the real-world environment on the client device.

Real-time fashion item transfer system

A system and a method for generating an automated GIF file generation system is described. In one aspect, the method includes accessing an animated GIF file, identifying a plurality of elements displayed in the animated GIF file, applying a variation of one or more elements to the animated GIF file, and generating a variant animated GIF file by applying the variation of the one or more elements to the animated GIF file. The system measures a trending metric of the variant animated GIF file based on a number of times the variant animated GIF file is shared on the communication platform and uses the trending metric as a feedback to generating the variant animated GIF file.

Automated GIF generation platform

Visual-inertial tracking of an eyewear device using a rolling shutter camera(s). The device includes a position determining system. Visual-inertial tracking is implemented by sensing motion of the device. An initial pose is obtained for a rolling shutter camera and an image of an environment is captured. The image includes feature points captured at a particular capture time. A number of poses for the rolling shutter camera is computed based on the initial pose and sensed movement of the device. The number of computed poses is responsive to the sensed movement of the mobile device. A computed pose is selected for each feature point in the image by matching the particular capture time for the feature point to the particular computed time for the computed pose. The position of the mobile device is determined within the environment using the feature points and the selected computed poses for the feature points.

Visual-inertial tracking using rolling shutter cameras

A method for adjusting camera intrinsic parameters of a single camera visual tracking device is described. In one aspect, a method includes accessing a temperature of a camera of the visual tracking system, detecting that the temperature of the camera exceeds a threshold, in response identifying one or more feature points that are located in a central region of an initial image, generating a graphical user interface element that instructs a user of the visual tracking system to move the visual tracking system towards a border region of the initial image, and determining intrinsic parameters of the camera based on matching pairs of the one or more detected feature points in the border region and one or more projected feature points in the border region.

Camera intrinsic re-calibration in mono visual tracking system

A method for recognizing sign language using collaborative augmented reality devices is described. In one aspect, a method includes accessing a first image generated by a first augmented reality device and a second image generated by a second augmented reality device, the first image and the second image depicting a hand gesture of a user of the first augmented reality device, synchronizing the first augmented reality device with the second augmented reality device, in response to the synchronizing, distributing one or more processes of a sign language recognition system between the first and second augmented reality devices, collecting results from the one or more processes from the first and second augmented reality devices, and displaying, in near real-time in a first display of the first augmented reality device, text indicating a sign language translation of the hand gesture based on the results.

Sign language interpretation with collaborative agents

An ergonomics evaluation system for AR applications of an AR device is described. In one aspect, a method includes accessing user interface elements of an augmented reality application, accessing a plurality of user models and corresponding simulated augmented reality device sensor data for the plurality of user models, identifying simulated user interactions, from the plurality of user models, with a simulated augmented reality device operating the augmented reality application, based on the plurality of user models and corresponding simulated augmented reality device sensor data for the plurality of user models, applying a computer vision algorithm to the simulated user interactions, identifying user postures and user motions based on the simulated user interactions, and generating a first ergonomic feedback based on the user postures and the user motions.

Augmented reality ergonomics evaluation system

A method for generating a virtual selfie stick image is described. In one aspect, the method includes generating, at a device, an original self-portrait image with an optical sensor of the device, the optical sensor directed at a face of a user of the device, the device being held at an arm length from the face of the user, displaying, on a display of the device, an instruction guiding the user to move the device at the arm length about the face of the user within a limited range at a plurality of poses, accessing, at the device, image data generated by the optical sensor at the plurality of poses, and generating a virtual selfie stick self-portrait image based on the original self-portrait image and the image data.

Virtual selfie stick

A method for transferring a gait pattern of a first user to a second user to simulate augmented reality content in a virtual simulation environment is described. In one aspect, the method includes identifying a gait pattern of a first user operating a first visual tracking system in a first physical environment, identifying a trajectory from a second visual tracking system operated by a second user in a second physical environment, the trajectory based on poses of the second visual tracking system over time, modifying the trajectory from the second visual tracking system based on the gait pattern of the first user, applying the modified trajectory in a plurality of virtual environments, and generating simulated ground truth data based on the modified trajectory in the plurality of virtual environments.

AR data simulation with gaitprint imitation

Systems and methods of generating ground truth datasets for producing virtual reality (VR) experiences, for testing simulated sensor configurations, and for training machine-learning algorithms. In one example, a recording device with one or more cameras and one or more inertial measurement units captures images and motion data along a real path through a physical environment. A SLAM application uses the captured data to calculate the trajectory of the recording device. A polynomial interpolation module uses Chebyshev polynomials to generate a continuous time trajectory (CTT) function. The method includes identifying a virtual environment and assembling a simulated sensor configuration, such as a VR headset. Using the CTT function, the method includes generating a ground truth output dataset that represents the simulated sensor configuration in motion along a virtual path through the virtual environment. The virtual path is closely correlated with the motion along the real path as captured by the recording device. Accordingly, the output dataset produces a realistic and life-like VR experience. In addition, the methods described can be used to generate multiple output datasets, at various sample rates, which are useful for training the machine-learning algorithms which are part of many VR systems.

Generating ground truth datasets for virtual reality experiences

Visual-inertial tracking of an eyewear device using a rolling shutter camera(s). The eyewear device includes a position determining system. Visual-inertial tracking is implemented by sensing motion of the eyewear device. An initial pose is obtained for a rolling shutter camera and an image of an environment is captured. The image includes feature points captured at a particular capture time. A number of poses for the rolling shutter camera is computed based on the initial pose and sensed movement of the device. The number of computed poses is responsive to the sensed movement of the mobile device. A computed pose is selected for each feature point in the image by matching the particular capture time for the feature point to the particular computed time for the computed pose. The position of the mobile device is determined within the environment using the feature points and the selected computed poses for the feature points.

Growing community of inventors

Wr. Neudorf, Austria

Kai Zhou