Systems and methods for generating stabilized images of a real environment in artificial reality

Patent metadata

Field	Value
Publication number	US-12033270-B2
Application number	US-202217972269-A
Country	US
Kind code	B2
Filing date	Oct 24, 2022
Priority date	Dec 30, 2020
Publication date	Jul 9, 2024
Grant date	Jul 9, 2024

Abstract

A method includes detecting an object of interest in a real environment and depth information of the object; determining one or more anchor locations in a three-dimensional space that correspond to a position of the object in the three-dimensional space; and generating a virtual surface anchored in the three-dimensional space. The method may further determine a pose of a camera when an image is captured and determine a region in the image that corresponds to the virtual surface. The method may further determine a first viewpoint of a first eye of the user; render a first output image based on (1) the first viewpoint relative to the virtual surface and (2) the image region corresponding to the virtual surface; and display the first output image on a first display of the computing device, the first display being configured to be viewed by the first eye of the user.

First claim

What is claimed is:

1. A method comprising, by a computing device:
detecting an object of interest in a real environment and depth information of the object;
determining, based on the depth information, one or more anchor locations in a three-dimensional space that correspond to a position of the object of interest in the three-dimensional space;
generating, based on the one or more anchor locations, a virtual surface anchored in the three-dimensional space;
determining a pose of a camera when an image is captured;
determining a region in the image that, as viewed from the pose of the camera, corresponds to the virtual surface;
determining a first viewpoint of a first eye of the user;
rendering a first output image based on (1) the first viewpoint relative to the virtual surface and (2) the image region corresponding to the virtual surface; and
displaying the first output image on a first display of the computing device, the first display being configured to be viewed by the first eye of the user.

2. The method of claim 1 , wherein the object of interest in the real environment is detected using a computer vision technique.

3. The method of claim 1 , wherein the one or more anchor locations are further determined based on one or more tracked motions of a hand of the user.

4. The method of claim 3 , wherein the tracking motions comprise designating a first coordinate in the three-dimensional space, wherein the one or more anchor locations are based on the first coordinate.

5. The method of claim 1 , wherein the three-dimensional space is a virtual reality environment.

6. The method of claim 1 , wherein the camera worn by the user is associated with a head-mounted device worn by the user that blocks the user from seeing the real environment directly.

7. The method of claim 1 , further comprising determining a horizontal distance of the user from the virtual surface; wherein displaying the first output image is based on the horizontal distance of the user from the virtual surface exceeding a minimum threshold distance.

8. The method of claim 1 , further comprising determining a vertical distance of the user from the virtual surface; wherein displaying the first output image is based on the vertical distance of the user from the virtual surface exceeding a minimum threshold distance.

9. The method of claim 1 , further comprising determining an orientation of the computing device relative to the virtual surface; wherein displaying the first output image is based on the orientation of the computing device.

10. The method of claim 1 , further comprising:
determining a second viewpoint of a second eye of the user;
rendering a second output image based on (1) the second viewpoint relative to the virtual surface and (2) the image region corresponding to the virtual surface; and
displaying the second output image on a second display of the computing device, the second display being configured to be viewed by the second eye of the user.

11. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
detect an object of interest in a real environment and depth information of the object;
determine, based on the depth information, one or more anchor locations in a three-dimensional space that correspond to a position of the object of interest in the three-dimensional space;
generate, based on the one or more anchor locations, a virtual surface anchored in the three-dimensional space;
determine a pose of a camera when an image is captured;
determine a region in the image that, as viewed from the pose of the camera, corresponds to the virtual surface;
determine a first viewpoint of a first eye of the user;
render a first output image based on (1) the first viewpoint relative to the virtual surface and (2) the image region corresponding to the virtual surface; and
display the first output image on a first display of the computing device, the first display being configured to be viewed by the first eye of the user.

12. The media of claim 11 , wherein the object of interest in the real environment is detected using a computer vision technique.

13. The media of claim 11 , wherein the one or more anchor locations are further determined based on one or more tracked motions of a hand of the user.

14. The media of claim 13 , wherein the tracking motions comprise designating a first coordinate in the three-dimensional space, wherein the one or more anchor locations are based on the first coordinate.

15. The media of claim 11 , wherein the three-dimensional space is a virtual reality environment.

16. The media of claim 11 , wherein the computing device is a head-mounted device that blocks the user from seeing the real environment directly.

17. The media of claim 11 , wherein the software is further operable when executed to determine a horizontal distance of the user from the virtual surface; wherein displaying the first output image is based on the horizontal distance of the user from the virtual surface.

18. A system comprising:
one or more processors; and
one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:
detect an object of interest in a real environment and depth information of the object;
determine, based on the depth information, one or more anchor locations in a three-dimensional space that correspond to a position of the object of interest in the three-dimensional space;
generate, based on the one or more anchor locations, a virtual surface anchored in the three-dimensional space;
determine a pose of a camera when an image is captured;
determine a region in the image that, as viewed from the pose of the camera, corresponds to the virtual surface;
determine a first viewpoint of a first eye of the user;
render a first output image based on (1) the first viewpoint relative to the virtual surface and (2) the image region corresponding to the virtual surface; and
display the first output image on a first display of the computing device, the first display being configured to be viewed by the first eye of the user.

19. The system of claim 18 , wherein the object of interest in the real environment is detected using a computer vision technique.

20. The system of claim 18 , wherein the one or more anchor locations are further determined based on one or more tracked motions of a hand of the user.

Assignees

• Meta Platforms Tech Llc

Inventors

• Marra Alessia
• Noris Gioacchino
• Inversin Panya

Classifications

• H04N5/272

  Means for inserting a foreground image in a background image, i.e. inlay, outlay · CPC title

• G09G2340/12

  Overlay of images, i.e. displayed pixel being the result of switching between the corresponding input pixels · CPC title

• G09G2340/10

  Mixing of images, i.e. displayed pixel being the result of an operation, e.g. adding, on the corresponding input pixels · CPC title

• G06T2207/30244

  Camera pose · CPC title

• G06T19/006

  Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00) · CPC title