Virtual 3D communications with participant viewpoint adjustment
A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include receiving second participant metadata and first viewpoint metadata by a first unit that is associated with a first participant, wherein the second participant metadata is indicative of a pose of a second participant and an expression of the second participant, wherein the first viewpoint metadata is indicative of a virtual position from which the first participant requests to view an avatar of the second participant; generating, by the first unit, and based on the second participant metadata and the first viewpoint metadata, a second participant representation information; wherein the second participant representation information comprises a compact 3D model of the second participant and a second participant texture map; and determining, for the first participant and during the 3D video conference, a representation of virtual 3D video conference environment, wherein the determining is based on the second participant representation information.
1. A method for conducting a three dimensional (3D) video conference between multiple participants, the method comprises:
receiving second participant metadata and first viewpoint metadata by a first unit that is associated with a first participant, wherein the second participant metadata is indicative of a pose of a second participant and an expression of the second participant, wherein the first viewpoint metadata is indicative of a virtual position from which the first participant requests to view an avatar of the second participant;
generating, by the first unit, and based on the second participant metadata and the first viewpoint metadata, a second participant representation information; wherein the second participant representation information comprises a compact 3D model of the second participant and a second participant texture map; and
determining, for the first participant and during the 3D video conference, a representation of virtual 3D video conference environment, wherein the determining comprises: determining an estimate of an appearance of the second participant in the virtual 3D video conference environment based on the second participant texture map; and amending the estimate based on a compact 3D model of at least the second participant.
2. The method according to claim 1 comprising generating each one of the compact 3D model and the second participant texture map in response to the second participant metadata and first viewpoint metadata.
3. The method according to claim 1 wherein the generating of at least one of the compact 3D model and the second participant texture map comprises feeding the second participant metadata and first viewpoint metadata to one or more neural networks trained to output the at least one of the compact 3D model and the second participant texture map based on the second participant metadata and first viewpoint metadata.
4. The method according to claim 1 wherein the compact 3D model comprises less than ten thousand points.
5. The method according to claim 1 wherein the compact 3D model consists essentially of five thousand points.
6. The method according to claim 1 wherein the amending comprises amending the estimate based on concealment and illumination effects related to compact 3D models of one or more participants of the 3D conference video.
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:
receiving second participant metadata and first viewpoint metadata by a first unit that is associated with a first participant, wherein the second participant metadata is indicative of a pose of a second participant and an expression of the second participant, wherein the first viewpoint metadata is indicative of a virtual position from which the first participant requests to view an avatar of the second participant;
generating, by the first unit, and based on the second participant metadata and the first viewpoint metadata, a second participant representation information; wherein the second participant representation information that stores instructions for a compact 3D model of the second participant and a second participant texture map; and
determining, for the first participant and during the 3D video conference, a representation of virtual 3D video conference environment, wherein the determining comprises determining an estimate of an appearance of the second participant in the virtual 3D video conference environment based on the second participant texture map; and amending the estimate based on a compact 3D model of at least the second participant.
8. The non-transitory computer readable medium according to claim 7 comprising generating each one of the compact 3D model and the second participant texture map are in response to the second participant metadata and first viewpoint metadata.
9. The non-transitory computer readable medium according to claim 7 wherein the generating of at least one of the compact 3D model and the second participant texture map that stores instructions for feeding the second participant metadata and first viewpoint metadata to one or more neural networks trained to output the at least one of the compact 3D model and the second participant texture map based on the second participant metadata and first viewpoint metadata.
10. The non-transitory computer readable medium according to claim 7 wherein the compact 3D model that stores instructions for less than ten thousand points.
11. The non-transitory computer readable medium according to claim 7 wherein the compact 3D model consists essentially of five thousand points.
12. The non-transitory computer readable medium according to claim 7 wherein the amending that stores instructions for amending the estimate based on concealment and illumination effects related to compact 3D models of one or more participants of the 3D conference video.