Selecting viewpoints for rendering in volumetric video presentations

1. A method comprising:

receiving, by a processor, a plurality of video streams depicting a scene, wherein the plurality of video streams provides images of the scene from a plurality of different viewpoints;

identifying, by the processor, a target that is present in the scene, wherein the target is identified based on a determination of a likelihood of being of interest to a viewer of the scene;

determining, by the processor, a trajectory of the target through the plurality of video streams, wherein the determining is based in part on an automated visual analysis of the plurality of video streams;

rendering, by the processor, a volumetric video traversal that follows the target through the scene, wherein the rendering comprises compositing the plurality of video streams;

receiving, by the processor, viewer feedback regarding the volumetric video traversal; and

adjusting, by the processor, the rendering in response to the viewer feedback, wherein the adjusting comprises sending, by the processor, an instruction to a movable camera instructing the movable camera to capture images of the scene from a new viewpoint.

2. The method of claim 1 , wherein the target is an object.

3. The method of claim 1 , wherein the target is an individual.

4. The method of claim 1 , wherein the target is a location.

5. The method of claim 1 , wherein the target is an action.

6. The method of claim 1 , wherein the identifying comprises:

identifying, by the processor, a preference for the target in a stored profile associated with the viewer.

7. The method of claim 1 , wherein the identifying comprises:

receiving, by the processor, a request from the viewer to follow the target.

8. The method of claim 1 , wherein the identifying comprises:

identifying, by the processor, a group of viewers who share a similarity with the viewer; and

selecting, by the processor, an item for which the group of viewers have previously expressed a preference as the target.

9. The method of claim 1 , wherein the identifying comprises:

selecting, by the processor, an item that was previously of interest to the viewer in a media that is thematically similar to the scene as the target.

10. The method of claim 1 , wherein the identifying comprises:

selecting, by the processor, a viewer-requested target from a previous scene as the target.

11. The method of claim 1 , wherein the identifying comprises:

receiving, by the processor, a request from a creator of the scene to follow the target.

12. The method of claim 1 , wherein the rendering comprises:

selecting, by the processor, a subset of the plurality of video streams that presents the target in a manner consistent with a preference of the viewer; and

performing, by the processor, the compositing using the subset.

13. The method of claim 12 , wherein the preference comprises a preference with respect to a cinematographic effect.

14. The method of claim 12 , wherein the preference comprises a preference with respect to a subject matter the viewer does not want to see.

15. The method of claim 12 , wherein the adjusting further comprises:

selecting, by the processor, a new subset of the video streams in response to the viewer feedback; and

performing, by the processor, the compositing using the new subset.

16. The method of claim 1 , wherein the adjusting further comprises:

identifying, by the processor, a new target that is present in the scene, wherein the new target is identified based on a new determination of a likelihood of being of interest to the viewer of the scene;

determining, by the processor, a new trajectory of the new target through the plurality of video streams, wherein the determining the new trajectory is based in part on a visual analysis of the plurality of video streams; and

adjusting, by the processor, the rendering so that the volumetric video traversal now follows the new target through the scene.

17. The method of claim 1 , further comprising:

selecting, by the processor, a new target in a new scene, in response to the viewer feedback.

18. A non-transitory computer-readable storage medium storing instructions which, when executed by a processor, cause the processor to perform operations, the operations comprising:

receiving a plurality of video streams depicting a scene, wherein the plurality of video streams provides images of the scene from a plurality of different viewpoints;

identifying a target that is present in the scene, wherein the target is identified based on a determination of a likelihood of being of interest to a viewer of the scene;

determining a trajectory of the target through the plurality of video streams, wherein the determining is based in part on an automated visual analysis of the plurality of video streams;

rendering a volumetric video traversal that follows the target through the scene, wherein the rendering comprises compositing the plurality of video streams;

receiving viewer feedback regarding the volumetric video traversal; and

adjusting the rendering in response to the viewer feedback, wherein the adjusting comprises sending an instruction to a movable camera instructing the movable camera to capture images of the scene from a new viewpoint.

19. A system comprising:

a processor deployed in a telecommunication service provider network; and

a non-transitory computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising:

receiving a plurality of video streams depicting a scene, wherein the plurality of video streams provides images of the scene from a plurality of different viewpoints;

identifying a target that is present in the scene, wherein the target is identified based on a determination of a likelihood of being of interest to a viewer of the scene;

determining a trajectory of the target through the plurality of video streams, wherein the determining is based in part on an automated visual analysis of the plurality of video streams;

rendering a volumetric video traversal that follows the target through the scene, wherein the rendering comprises compositing the plurality of video streams;

receiving viewer feedback regarding the volumetric video traversal; and

adjusting the rendering in response to the viewer feedback, wherein the adjusting comprises sending an instruction to a movable camera instructing the movable camera to capture images of the scene from a new viewpoint.

20. The non-transitory computer-readable storage medium of claim 18 , wherein the rendering comprises:

selecting a subset of the plurality of video streams that presents the target in a manner consistent with a preference of the viewer; and

performing the compositing using the subset.