Virtual 3D communications that include reconstruction of hidden face areas
A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include determining, for each participant, updated 3D participant representation information within the virtual 3D video conference environment, that represents participants; wherein the determining comprises estimating 3D participant representation information of one or more hidden areas of a face of a participant that are hidden from the camera that captures at least one visible area of the face of the participant; and generating, for at least one participant, an updated representation of virtual 3D video conference environment, the updated representation of virtual 3D video conference environment represents the updated 3D participant representation information for at least some of the multiple participants.
1. A method for conducting a three dimensional (3D) video conference between multiple participants, the method comprises:
determining, for each participant, updated 3D participant representation information within the virtual 3D video conference environment, that represents participants; wherein the determining comprises estimating 3D participant representation information of one or more hidden areas of a face of a participant that are hidden from the camera that captures at least one visible area of the face of the participant; and
generating, for at least one participant, an updated representation of virtual 3D video conference environment, the updated representation of virtual 3D video conference environment represents the updated 3D participant representation information for at least some of the multiple participants.
2. The method according to claim 1 comprising estimating 3D model hidden areas and one or hidden parts texture maps.
3. The method according to claim 1 wherein the estimating 3D participant representation information of one or more hidden areas is executed by using one or more generative adversarial networks.
4. The method according to claim 1 wherein the updated 3D participant representation of a participant is an avatar of the respective participant.
5. The method according to claim 4 , comprising determining a size of the avatar.
6. The method according to claim 1 , wherein the representation of virtual 3D video conference environment represents at least a direction of gaze of at least one of the participants.
7. A non-transitory computer readable medium for conducting a three dimensional (3D) video conference between multiple participants, the non-transitory computer readable medium that stores instructions for:
determining, for each participant, updated 3D participant representation information within the virtual 3D video conference environment, that represents participant; wherein the determining that stores instructions for estimating 3D participant representation information of one or more hidden areas of a face of a participant that are hidden from the camera that captures at least one visible area of the face of the participant; and
generating, for at least one participant, an updated representation of virtual 3D video conference environment, the updated representation of virtual 3D video conference environment represents the updated 3D participant representation information for at least some of the multiple participants.
8. The non-transitory computer readable medium according to claim 7 that stores instructions for estimating 3D model hidden areas and one or hidden parts texture maps.
9. The non-transitory computer readable medium according to claim 7 wherein the estimating 3D participant representation information of one or more hidden areas is executed by using one or more generative adversarial networks.
10. The non-transitory computer readable medium according to claim 7 wherein the updated 3D participant representation of a participant is an avatar of the respective participant.
11. The non-transitory computer readable medium according to claim 10 , that stores instructions for determining a size of the avatar.
12. The non-transitory computer readable medium according to claim 7 , wherein the representation of virtual 3D video conference environment represents at least a direction of gaze of at least one of the participants.