Generating a 3D visual representation of the 3D object using a neural network selected out of multiple neural networks

1. A method for generating a three dimensional (3D) visual representation of a sensed object that is three dimensional, the method comprises:

obtaining a 3D visual representation parameter, the visual representation parameters is selected out of a size parameter, a resolution parameter, and a resource consumption parameter;

obtaining object information that represents the sensed object;

selecting, based on a value of the 3D visual representation parameter, a selected neural network for generating the visual representation of the sensed object; wherein the selected neural network is selected out of a group of neural networks, wherein different neural networks of the group are associated with different values of the 3D visual representation parameter

and

generating the 3D visual representation of the 3D object by the selected neural network, without using other neural networks of the group that are associated with other values of the 3D visual representation.

2. The method according to claim 1 wherein the generating of the visual representation comprising generating a 3D model of the 3D object and at least one 2D texture map of the 3D object.

3. The method according to claim 2 wherein the generating comprises further processing the 3D model and the 2D texture map during a rendering process of at least one rendered image.

4. The method according to claim 2 wherein the generating is executed by a first computerized unit, wherein the generating is followed by sending the 3D model and the at least one 2D texture map to a second computerized unit configured to render at least one rendered image based on the 3D model and the at least one 2D texture map.

5. The method according to claim 1 wherein the 3D object is a participant of a 3D video conference.

6. The method according to claim 1 comprising outputting the 3D visual representation from the selected set of neural network outputs.

7. The method according to claim 6 wherein the 3D object is a participant of a 3D video conference.

8. The method according to claim 1 , wherein the 3D object is a second participant of a 3D video conference, wherein the obtaining of the 3D visual representation parameter comprises (i) receiving a zoom level requested by a first participant of the 3D video conference; (ii) determining a size of an image of the second participant in a virtual environment displayed to the first participant during the 3D video conference, and (ii) determining, based on the size, the value of a resolution of the selected neural network.

9. The method according to claim 8 , wherein the value of resolution is lower than a highest resolution associated with a highest resolution neural network of the group;

and wherein the generating of the 3D visual representation of the 3D object by the selected neural network involves performing less calculation in relation to a generation of the 3D visual representation of the 3D object by the highest resolution neural network.

10. A non-transitory computer readable medium for generating a three dimensional (3D) visual representation of a sensed object that is three dimensional, the non-transitory computer readable medium that stores instructions for:

obtaining a 3D visual representation parameter, the 3D visual representation parameters is selected out of a size parameter, a resolution parameter, and a resource consumption parameter;

obtaining object information that represents the sensed object;

selecting, based on a value of the 3D visual representation parameter, a selected neural network for generating the visual representation of the sensed object; wherein the selected neural network is selected out of a group of neural networks, wherein different neural networks of the group are associated with different values of the 3D visual representation parameter; and

generating the 3D visual representation of the 3D object by the selected neural network, without using other neural networks of the group that are associated with other values of the 3D visual representation.

11. The non-transitory computer readable medium according to claim 10 wherein the generating of the visual representation comprising generating a 3D model of the 3D object and at least one 2D texture map of the 3D object.

12. The non-transitory computer readable medium according to claim 11 wherein the generating comprises further processing the 3D model and the 2D texture map during a rendering process of at least one rendered image.

13. The non-transitory computer readable medium according to claim 11 wherein the generating is executed by a first computerized unit, wherein the generating is followed by sending the 3D model and the at least one 2D texture map to a second computerized unit configured to render at least one rendered image based on the 3D model and the at least one 2D texture map.

14. The non-transitory computer readable medium according to claim 10 wherein the 3D object is a participant of a 3D video conference.

15. The non-transitory computer readable medium according to claim 10 that stores instructions for outputting the 3D visual representation from the selected set of neural network outputs.

16. The non-transitory computer readable medium according to claim 15 wherein the 3D object is a participant of a 3D video conference.

17. The non-transitory computer readable medium according to claim 10 , wherein the 3D object is a second participant of a 3D video conference, wherein the obtaining of the 3D visual representation parameter comprises (i) receiving a zoom level requested by a first participant of the 3D video conference; (ii) determining a size of an image of the second participant in a virtual environment displayed to the first participant during the 3D video conference, and (ii) determining, based on the size, the value of a resolution of the selected neural network.

18. The non-transitory computer readable medium according to claim 17 , wherein the value of resolution is lower than a highest resolution associated with a highest resolution neural network of the group; and wherein the generating of the 3D visual representation of the 3D object by the selected neural network involves performing less calculation in relation to a generation of the 3D visual representation of the 3D object by the highest resolution neural network.