Building virtual reality (VR) gaming environments using real-world virtual reality maps

1. A method, comprising:

accessing a base VR model of a real-world environment from a third party mapping data store, wherein the real-world environment includes a plurality of real-world objects;

detecting a first real-world object in the real-world environment based on one or more images or videos of the real-world environment provided as input into a deep learning engine including a plurality of learned models of objects, wherein the deep learning engine includes a network of interconnected nodes within an input layer, one or more hidden layers, and an output layer;

augmenting a first object in the base VR model that corresponds to the first real-world object in the real-world environment;

stitching in the first object that is augmented into the base VR model to generate an augmented base VR model;

storing the augmented base VR model to a library data store comprising a plurality of augmented base VR models; and

using one or more of the plurality of augmented base VR models to define a virtual environment of a gaming application.

2. The method of claim 1 , further comprising:

receiving a request for the one or more of the plurality of augmented base VR models from a remote device; and

sending the one or more of the plurality of augmented base VR models to the remote device for interfacing with a game logic of the gaming application, wherein the game logic is executing on the remote device in association with a game play of a first user.

3. The method of claim 2 , wherein the remote device is a server configured to execute a plurality of game logics for a plurality of gaming applications for a plurality of users.

4. The method of claim 2 , wherein the remote device is a console of the first user.

5. The method of claim 1 , further comprising:

making available the augmented base VR model from the library data store through a software development kit (SDK) to a remote device for use in developing a game logic of the gaming application configured to interface with the augmented base VR model.

6. The method of claim 1 , wherein the augmenting the first object includes:

determining that a first surface model of the first real-world object in the real-world environment is incomplete in the base VR model, wherein the base VR model includes a plurality of surface models, each surface model associated with a corresponding real-world object;

accessing a plurality of images of the first real-world object from an object data store;

augmenting the first surface model that is incomplete with a surface segment built from the plurality of images of the first real-world object to generate an augmented first surface model; and

using the augmented first surface model for the first surface model that is incomplete when performing the stitching.

7. The method of claim 1 , wherein the augmenting the first object includes:

determining that a first surface model of the first real-world object in the real-world environment is incomplete in the base VR model, wherein the base VR model includes a plurality of surface models, each surface model associated with a corresponding real-world object;

accessing a previously generated complete first surface model from an object data store; and

using the previously generated complete first surface model to represent the first real- world object when performing the stitching.

8. The method of claim 1 , wherein the augmenting the first object includes:

determining that a first surface model of the first real-world object in the real-world environment is incomplete in the base VR model, wherein the base VR model includes a plurality of surface models, each surface model associated with a corresponding real-world object;

accessing a plurality of images of the first real-world object from an object data store;

generating a complete first surface model of the first real-world object using the plurality of images; and

using the complete first surface model to represent the first real-world object when performing the stitching.

9. The method of claim 1 , further comprising:

determining a gap region in the base VR model, wherein the gap region is devoid of at least one object;

accessing a filler object to fill in the gap region; and

stitching in the filler object into the base VR model to generate the augmented base VR model.

10. The method of claim 1 , wherein the real-world environment comprises one of a live event, a museum, and a city.

11. A non-transitory computer-readable medium storing a computer program, the computer-readable medium comprising:

program instructions for accessing a base VR model of a real-world environment from a third party mapping data store, wherein the real-world environment includes a plurality of real-world objects;

program instructions for detecting a first real-world object in the real-world environment based on one or more images or videos of the real-world environment provided as input into a deep learning engine including a plurality of learned models of objects, wherein the deep learning engine includes a network of interconnected nodes within an input layer, one or more hidden layers, and an output layer;

program instructions for augmenting a first object in the base VR model that corresponds to the first real-world object in the real-world environment;

program instructions for stitching in the first object that is augmented into the base VR model to generate an augmented base VR model;

program instructions for storing the augmented base VR model to a library data store comprising a plurality of augmented base VR models; and

program instructions for using one or more of the plurality of augmented base VR models to define a virtual environment of a gaming application.

12. The computer-readable medium of claim 11 , further comprising:

program instructions for receiving a request for the one or more of the plurality of augmented base VR models from a remote device; and

program instructions for sending the one or more of the plurality of augmented base VR models to the remote device for interfacing with a game logic of the gaming application, wherein the game logic is executing on the remote device in association with a game play of a first user.

13. The computer-readable of claim 11 , further comprising:

program instructions for making available the augmented base VR model from the library data store through a software development kit (SDK) to a remote device for use in developing a game logic of the gaming application configured to interface with the augmented base VR model.

14. The computer-readable of claim 11 , wherein the program instructions for augmenting the first object comprises:

program instructions for determining that a first surface model of the first real-world object in the real-world environment is incomplete in the base VR model, wherein the base VR model includes a plurality of surface models, each surface model associated with a corresponding real-world object;

accessing a plurality of images of the first real-world object from an object data store;

augmenting the first surface model that is incomplete with a surface segment built from the plurality of images of the first real-world object to generate an augmented first surface model; and

using the augmented first surface model for the first surface model that is incomplete when performing the stitching in the first object that is augmented.

15. The computer-readable of claim 11 , further comprising:

program instructions for determining a gap region in the base VR model, wherein the gap region is devoid of at least one object;

program instructions for accessing a filler object to fill in the gap region; and

program instructions for stitching in the filler object into the base VR model to generate the augmented base VR model.

16. A computer system comprising:

a processor; and

memory coupled to the processor and having stored therein instructions that, if executed by the computer system, cause the computer system to execute a method comprising:

accessing a base VR model of a real-world environment from a third party mapping data store, wherein the real-world environment includes a plurality of real-world objects;

detecting a first real-world object in the real-world environment based on one or more images or videos of the real-world environment provided as input into a deep learning engine including a plurality of learned models of objects, wherein the deep learning engine includes a network of interconnected nodes within an input layer, one or more hidden layers, and an output layer;

augmenting a first object in the base VR model that corresponds to the first real-world object in the real-world environment;

stitching in the first object that is augmented into the base VR model to generate an augmented base VR model;

storing the augmented base VR model to a library data store comprising a plurality of augmented base VR models; and

using one or more of the plurality of augmented base VR models to define a virtual environment of a gaming application.

17. The computer system of claim 16 , wherein the method further comprises:

receiving a request for the one or more of the plurality of augmented base VR models from a remote device; and

sending the one or more of the plurality of augmented base VR models to the remote device for interfacing with a game logic of the gaming application, wherein the game logic is executing on the remote device in association with a game play of a first user.

18. The computer system of claim 16 , wherein the method further comprises:

making available the augmented base VR model from the library data store through a software development kit (SDK) to a remote device for use in developing a game logic of the gaming application configured to interface with the augmented base VR model.

19. The computer system of claim 16 , wherein the augmenting the first object in the method comprises:

determining that a first surface model of the first real-world object in the real-world environment is incomplete in the base VR model, wherein the base VR model includes a plurality of surface models, each surface model associated with a corresponding real-world object;

accessing a plurality of images of the first real-world object from an object data store;

augmenting the first surface model that is incomplete with a surface segment built from the plurality of images of the first real-world object to generate an augmented first surface model; and

using the augmented first surface model for the first surface model that is incomplete when performing the stitching.

20. The computer system of claim 16 , wherein the method further comprises:

determining a gap region in the base VR model, wherein the gap region is devoid of at least one object;

accessing a filler object to fill in the gap region; and

stitching in the filler object into the base VR model to generate the augmented base VR model.