Granted Patent B1

US 12,394,146 · App. 17/947,503 · Granted Aug 19, 2025

Inventors: Mark E. Drummond (Palo Alto, CA); Daniel L. Kovacs (Santa Clara, CA); Shaun D. Budhram (Los Gatos, CA); Edward Ahn (San Francisco, CA); Behrooz Mahasseni (San Jose, CA); Aashi Manglik (Sunnyvale, CA); Payal Jotwani (Santa Clara, CA); Mu Qiao (Campbell, CA); Bo Morgan (Emerald Hills, CA); Noah Gamboa (San Franciso, CA); Michael J. Gutensohn (San Francisco, CA); Dan Feng (Santa Clara, CA); Siva Chandra Mouli Sivapurapu (Santa Clara, CA)

Assignee: Apple Inc.

G06T17/00G06F3/013G06V10/987

Abstract

Claims (44)

1. A method comprising:

at a device including a display, one or more processors, and non-transitory memory:

generating a definition of a scene based on textual or speech input and a model of an environment, wherein the definition of the scene includes a constraint that defines a spatial relationship between a virtual asset and an anchor asset that corresponds to one or more objects in the environment;

generating, based on application of the definition of the scene to a first physical environment, a first instance of the scene that satisfies the constraint with the virtual asset in the spatial relationship with a first one of the one or more objects in the first physical environment;

presenting, on the display, the first instance of the scene;

generating, based on application of the definition of the scene to a second physical environment, a second instance of the scene that satisfies the constraint with the virtual asset in the spatial relationship with a second one of the one or more objects in the second physical environment; and

presenting, on the display, the second instance of the scene.

2. The method of claim 1 , further comprising:

receiving, from a user, user feedback regarding the first instance of the scene; and

modifying the definition of the scene based on the user feedback.

3. The method of claim 2 , wherein the user feedback includes a positive indication or a negative indication.

4. The method of claim 2 , wherein the user feedback includes a numerical ranking.

5. The method of claim 2 , wherein the user feedback includes a preference between the first instance of the scene and a second instance of the scene.

6. The method of claim 2 , wherein the user feedback includes gaze information of the user.

7. The method of claim 2 , wherein modifying the definition of the scene includes adding or modifying a definition of a property of the virtual asset or the anchor asset.

8. The method of claim 7 , wherein adding or modifying the definition of the property is based on a user acceptance of a proposed addition or modification.

9. The method of claim 2 , wherein modifying the definition of the scene includes modifying a reward function.

10. The method of claim 2 , wherein modifying the definition of the scene includes modifying a neural network.

11. The method of claim 1 , wherein the second instance of the scene is displayed simultaneously with the first instance of the scene.

12. A device comprising:

a display;

non-transitory memory; and

one or more processors to:

obtain a definition of a scene, wherein the definition of the scene includes a constraint that defines a spatial relationship between a virtual asset and an anchor asset that corresponds to one or more objects in an environment;

generate, based on application of the definition of the scene to a first environment, a first instance of the scene that satisfies the constraint with the virtual asset in the spatial relationship with a first one of the one or more objects in the first environment;

generate, based on application of the definition of the scene to a second environment, a second instance of the scene that satisfies the constraint with the virtual asset in the spatial relationship with a second one of the one or more objects in the second environment; and

simultaneously present, on the display, the first instance of the scene and the second instance of the scene.

13. The device of claim 12 , wherein the one or more processors are further to:

receive, from a user, user feedback regarding the first instance of the scene and the second instance of the scene; and

modify the definition of the scene based on the user feedback.

14. The device of claim 13 , wherein the user feedback includes a preference between the first instance of the scene and the second instance of the scene.

15. The device of claim 13 , wherein the one or more processors are to modify the definition of the scene by adding or modifying a definition of a property of the virtual asset or the anchor asset.

16. The device of claim 12 , wherein the first environment is a first physical environment and the second environment is a first virtual environment.

17. A non-transitory memory having instructions encoded thereon which, when executed by one or more processors of a device, cause the device to:

obtain a definition of a scene, wherein the definition of the scene includes a definition of a property of an environment and a definition of a spatial relationship between a virtual asset and an anchor asset corresponding to one or more objects in the environment;

obtain a first virtual environment with the property;

present, on a display and based on application of the definition of the scene to the first virtual environment, a first instance of the scene including the virtual asset in the spatial relationship with a first object in the first virtual environment corresponding to the anchor asset;

obtain a second virtual environment with the property; and

present, on the display and based on application of the definition of the scene to the second virtual environment, a second instance of the scene including the virtual asset in the spatial relationship with a second object in the second virtual environment corresponding to the anchor asset.

18. The non-transitory memory of claim 17 , wherein the first virtual environment is based on a physical environment remote from the device.

19. The non-transitory memory of claim 17 , wherein the instructions, when executed, further cause the device to:

receive, from a user, user feedback regarding the first instance of the scene; and

modify the definition of the scene based on the user feedback.

20. The non-transitory memory of claim 19 , wherein the user feedback includes a positive indication or a negative indication.

Assignments (1)

Continuity (1)

References Cited (15)