Geometry modeling of eyewear devices with flexible frames
An eyewear device with flexible frame for Augmented Reality (AR) is disclosed. At least two sensors and a display are mounted on the flexible frame. When in use, the real time geometry of the eyewear device may change from factory calibrated geometry, resulting in low quality AR rendering. A modeling module is provided to model the real time geometry of the eyewear device on the fly using sensor information of the at least two sensors. The modeled real time geometry is then provided to a rendering module to accurately display the AR to the user.
1. A system comprising:
an eyewear device for displaying augmented reality images, comprising:
a first sensor;
a second sensor;
at least one display for displaying the augmented reality images; and
an augmented reality image rendering system configured to render the augmented reality images on the at least one display, to estimate a real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display, and to adjust the rendering of the augmented reality images on the at least one display using a bending curve model of a real-time geometry of the eyewear device based on the estimated real-time spatial relation between the any two or more of the first sensor, the second sensor, and the at least one display.
2. The system of claim 1 , wherein the augmented reality image rendering system is located in at least one of the eyewear device, a mobile computing device, or a server system.
3. The system of claim 1 , wherein the augmented reality image rendering system comprises an algorithm that models the bending curve of the eyewear device.
4. The system of claim 3 , wherein the bending curve that is at least one of asymmetrical, non-smooth, or uneven.
5. The system of claim 1 , wherein the augmented reality image rendering system comprises at least one of an Extended Kalman Filter (EKF)-driven motion tracking module, an optimization-based module that coordinates spatial relation optimization, or a machine learning-driven module that provide motion tracking.
6. The system of claim 1 , wherein the augmented reality image rendering system implements an end-to-end learned approach for tracking and modeling the real-time geometry of the eyewear device.
7. The system of claim 1 , wherein the augmented reality image rendering system receives sensor inputs from at least one of the first sensor or the second sensor and processes the sensor inputs to track motion of the any two or more of the first sensor, the second sensor, and the at least one display with respect to each other.
8. The system of claim 1 , wherein the augmented reality image rendering system receives factory calibration parameters as input and determines if the factory calibration parameters are still accurate for the estimated real-time spatial relation between the any two or more of the first sensor, the second sensor, and the at least one display.
9. The system of claim 1 , wherein the first sensor and the second sensor are one of an IMU (Inertial Measurement Unit) and a camera.
10. The system of claim 1 , wherein the at least one display comprises at least one waveguide and at least one projector.
11. A method for displaying augmented reality images on an eyewear device including a first sensor, a second sensor and at least one display for displaying the augmented reality images, comprising:
rendering the augmented reality images on the at least one display;
estimating a real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display; and
adjusting the rendering of the augmented reality images on the at least one display using a bending curve model of a real-time geometry of the eyewear device based on the estimated real-time spatial relation between the any two or more of the first sensor, the second sensor, and the at least one display.
12. The method of claim 11 , wherein estimating the real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display comprises modeling the bending curve of the eyewear device.
13. The method of claim 12 , wherein the bending curve is at least one of asymmetrical, non-smooth, or uneven.
14. The method of claim 11 , wherein estimating the real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display comprises providing motion tracking of the any two or more of the first sensor, the second sensor, and the at least one display using at least one of an Extended Kalman Filter (EKF)-driven motion tracking module, an optimization-based module that coordinates spatial relation optimization, or a machine learning-driven module that provides motion tracking.
15. The method of claim 11 , wherein estimating the real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display comprises implementing an end-to-end learned approach for tracking and modeling the real-time geometry of the eyewear device.
16. The method of claim 11 , wherein estimating the real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display comprises receiving and processing sensor inputs from at least one of the first sensor or the second sensor to track motion of the any two or more of the first sensor, the second sensor, and the at least one display with respect to each other.
17. The method of claim 11 , wherein estimating the real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display comprises receiving factory calibration parameters as input and determining if the factory calibration parameters are still accurate for the estimated real-time spatial relation between the any two or more of the first sensor, the second sensor, and the at least one display.
18. A non-transitory computer-readable medium comprising instructions stored therein that, when executed by one or more processors, cause the one or more processors to display augmented reality images on an eyewear device including a first sensor, a second sensor and at least one display for displaying the augmented reality images, by performing operations comprising:
rendering the augmented reality images on the at least one display;
estimating a real-time spatial relation between any two or more of the first sensor, the second sensor, and the at least one display; and
adjusting the rendering of the augmented reality images on the at least one display using a bending curve model of a real-time geometry of the eyewear device based on the estimated real-time spatial relation between the any two or more of the first sensor, the second sensor, and the at least one display.
19. The non-transitory computer-readable medium of claim 18 , further comprising instructions, that when executed by the one or more processors, cause the one or more processors to perform operations comprising providing motion tracking of the any two or more of the first sensor, the second sensor, and the at least one display using at least one of an Extended Kalman Filter (EKF)-driven motion tracking, spatial relation optimization, or machine learning-driven motion tracking.
20. The non-transitory computer-readable medium of claim 18 , further comprising instructions, that when executed by the one or more processors, cause the one or more processors to perform operations comprising receiving and processing sensor inputs from at least one of the first sensor or the second sensor to track motion of the any two or more of the first sensor, the second sensor, and the at least one display with respect to each other, and receiving and processing factory calibration parameters to determine if the factory calibration parameters are still accurate for the estimated real-time spatial relation between the any two or more of the first sensor, the second sensor, and the at least one display.