Creating a virtual object response to a user input

1. An apparatus comprising:

a memory configured to store a machine-learning model; and

a processor configured to:

receive, via a sensor of the apparatus, an external input from a user to control a virtual object displayed in a virtual space by the apparatus;

send a message comprising an identification of a type of the external input and a value of the external input, as measured by the sensor, to a machine-learning model, wherein the machine-learning model comprises a convolutional neural network (CNN) layer and a generative adversarial network (GAN),

identify by the CNN layer a first bounding box corresponding to an approximate location of the virtual object in a current image of the virtual space before the external input is applied and a second bounding box corresponding to a predicted location of the virtual object in a next image of the virtual space after the external input is applied,

receive by the GAN the second bounding box from the CNN layer,

predict a location of the virtual object in the next image based on the external input of the user and the second bounding box;

and

move the virtual object in the virtual space based on the predicted location of the virtual object in the next image.

2. The apparatus of claim 1 , wherein the processor is configured to:

receive the external input with respect to a current image of the virtual space, and

wherein, when the processor predicts the movement of the virtual object, the processor is further configured to:

predict the movement of the virtual object in a subsequent image of the virtual space.

3. The apparatus of claim 1 , wherein the processor is further configured to:

determine a type of a user interaction of the external input from a plurality of different possible types of the user interactions, and

wherein, when the processor predicts the movement of the virtual object, the processor is further configured to:

predict the movement of the virtual object based on the determined type of the user interaction.

4. The apparatus of claim 1 , wherein the processor is configured to:

receive a touch input on a touch screen, and

wherein, when the processor predicts the movement of the virtual object, the processor is further configured to:

predict the movement of the virtual object based on a pressure value and a distance of movement of the touch input on the touch screen.

5. The apparatus of claim 1 , wherein the processor is configured to:

receive one or more inputs from among:

an audio signal generated by a user speaking, an audio signal generated by the user clapping hands, and air pressure generated by the user blowing air, and

wherein, when the processor predicts the movement of the virtual object, the processor is further configured to:

predict the movement of the virtual object based on the one or more inputs.

6. The apparatus of claim 1 , wherein the processor is configured to:

determine a value of force and a direction of the force created by the external input, and

wherein, when the processor predicts the movement of the virtual object, the processor is further configured to:

predict the movement of the virtual object based on the value of the force and the direction of the force.

7. The apparatus of claim 1 , wherein the machine learning model is trained based on at least one of previously recorded images and previously recorded videos of a physical object that moves in physical space in response to user stimulus.

8. A method comprising:

receiving, via a sensor of an apparatus, an external input from a user to control a virtual object displayed in a virtual space by the apparatus;

sending, by the apparatus, a message comprising an identification of a type of the external input and a value of the external input, as measured by the sensor, to a machine-learning model, wherein the machine-learning model comprises a convolutional neural network (CNN) layer and a generative adversarial network (GAN);

identifying by the CNN layer a first bounding box corresponding to an approximate location of the virtual object in a current image of the virtual space before the external input is applied and a second bounding box corresponding to a predicted location of the virtual object in a next image of the virtual space after the external input is applied;

receiving by the GAN the second bounding box from the CNN layer;

predicting a location of the virtual object in the next image based on the external input of the user and the second bounding box;

and

moving, by the apparatus, the virtual object in the virtual space based on the predicted location of the virtual object in the next image.

9. The method of claim 8 , wherein the receiving further comprises:

receiving the external input with respect to a current image of the virtual space, and

wherein the predicting further comprises:

predicting the movement of the virtual object in a subsequent image of the virtual space.

10. The method of claim 8 , wherein the receiving further comprises:

determining a type of user interaction of the external input from a plurality of different possible types of the user interactions, and

wherein the predicting further comprises:

predicting the movement of the virtual object based on the determined type of the user interaction.

11. The method of claim 8 , wherein the receiving further comprises:

receiving a touch input on a touch screen, and

wherein the predicting further comprises:

predicting the movement of the virtual object based on a pressure value and a distance of movement of the touch input on the touch screen.

12. The method of claim 8 , wherein the receiving further comprises:

receive one or more inputs from among:

an audio signal generated by a user speaking, an audio signal generated by the user clapping hands, and air pressure generated by the user blowing air, and

wherein the predicting further comprises:

predicting the movement of the virtual object in virtual space based on the one or more inputs.

13. The method of claim 8 , further comprising:

determining a value of force and a direction of the force created by the external input of the user, and

wherein the predicting further comprises:

predicting the movement of the virtual object in virtual space based on the value of the force and the direction of the force.

14. The method of claim 8 , wherein the machine learning model is trained based on at least one of previously recorded images and previously recorded videos of a physical object that moves in physical space in response to user stimulus.

15. A computer program product comprising a computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform:

receiving, via a sensor of an apparatus, an external input from a user to control a virtual object displayed in a virtual space by the apparatus;

sending, by the apparatus, a message comprising an identification of a type of the external input and a value of the external input, as measured by the sensor, to a machine-learning model, wherein the machine-learning model comprises a convolutional neural network (CNN) layer and a generative adversarial network (GAN);

identifying by the CNN layer a first bounding box corresponding to an approximate location of the virtual object in a current image of the virtual space before the external input is applied and a second bounding box corresponding to a predicted location of the virtual object in a next image of the virtual space after the external input is applied;

receiving by the GAN the second bounding box from the CNN layer;

predicting a location of the virtual object in the next image based on the external input of the user and the second bounding box;

and

moving, by the apparatus, the virtual object in the virtual space based on the predicted location of the virtual object in the next image.

16. The computer program product of claim 15 , wherein the receiving further comprises:

receiving the external input with respect to a current image of the virtual space, and

wherein the predicting further comprises:

predicting the movement of the virtual object in a subsequent image of the virtual space.