Electronic device and method for providing output images under reduced light level

1. An electronic device comprising:

an infrared (IR) camera configured to obtain user image data and user profile image data;

a processor;

a data storage device having executable instructions accessible by the processor;

wherein, responsive to execution of the instructions, the processor:

generates latent space data based on the user image data and user profile image data;

obtains model image data including at least one image of an individual other than the user, and model the user image data with the model image data to generate the latent space data; and

forms an output image of the user using generative modeling of the latent space data based on the user image data and the model image data.

2. The electronic device of claim 1 , wherein to generate the latent space data, the processor is further configured to model the user profile image data and user image data obtained by the IR camera using a probability distribution.

3. The electronic device of claim 1 , wherein the model image data utilized to form the output image of the user includes plural images of individuals other than a user.

4. The electronic device of claim 1 , wherein to generate the latent space data, the processor is further configured to provide affine transformation mapping of the user profile image data and the user image data obtained by the IR camera.

5. The electronic device of claim 1 , wherein to form the output image using generative modeling includes generative modeling the latent space data with noise with a first generative adversarial network to provide an encoded input for a second generative adversarial network that forms the output image.

6. The electronic device of claim 1 , wherein the processor is further configured to:

prompt a user to provide the user profile image data.

7. The electronic device of claim 1 , wherein a user appearance network generates the latent space data, and a synthesis network forms the output image.

8. The electronic device of claim 1 , wherein the IR camera is a red-green-blue IR camera.

9. The electronic device of claim 1 , wherein the IR camera is coupled to a bezel of the electronic device.

10. The electronic device of claim 1 , wherein the at least one image of the individual other than the user includes a first image generated by the electronic device and a second image of a real life individual that is not the user.

11. A method, comprising:

under control of one or more processors including program instructions to:

obtain user image data and user profile image data from an infrared (IR) camera;

generate latent space data based on the user image data and user profile image data;

obtain model image data including at least one image of an individual other than the user, and model the user image data with the model image data to generate the latent space data; and

form an output image of the user using generative modeling of the latent space data based on the user image data and the model image data.

12. The method of claim 11 , further comprising under the control of the one or more processors including program instructions to model the user profile image data and user image data obtained by the IR camera using a probability distribution to generate the latent space data.

13. The method of claim 11 further comprising under the control of the one or more processors including program instructions to provide affine transformation mapping of the user profile image data and the user image data to generate the latent space data.

14. The method of claim 11 , further comprising under the control of the one or more processors including program instructions to generative model the latent space data with noise with a first generative adversarial network to provide an encoded input for a second generative adversarial network that forms the output image.

15. The method of claim 11 , further comprising generating the at least one image of the individual other than the user.

16. A computer program product comprising a non-signal computer readable storage medium comprising computer executable code to automatically:

obtain user image data and user profile image data;

generate latent space data with a user appearance network based on the user image data and user profile image data;

obtain model image data including at least one image of an individual other than the user, and model the user image data with the model image data to generate the latent space data; and

form an output image of the user with a synthesis network using generative modeling of the latent space data based on the user image data and the model image data.

17. The computer program product of claim 16 , further comprising computer executable code to automatically model the user profile image data and user image data obtained using a probability distribution to generate the latent space data.

18. The computer program product of claim 16 , further comprising computer executable code to automatically provide affine transformation mapping of the user profile image data and the user image data to generate the latent space data.

19. The computer program product of claim 16 , further comprising computer executable code to automatically generative model the latent space data with noise with a first generative adversarial network to provide an encoded input for a second generative adversarial network that forms the output image.

20. The computer program product of claim 16 , further comprising computer executable code to generate the at least one image of the individual other than the user.