Enhanced Emotive Engagement with Volumetric Content

Abstract

A volumetric content enhancement system (“the system”) can annotate at least a portion of a plurality of voxels from a volumetric video with contextual data. The system can determine at least one actionable position within the volumetric video. The system can create an annotated volumetric video that includes the volumetric video, an annotation with the contextual data, and the at least one actionable position. The system can provide the annotated volumetric video to a volumetric content playback system. The system can obtain viewer feedback associated with the viewer and can determine an emotional state of the viewer based, at least in part, upon the viewer feedback. The system can receive viewer position information that identifies a specific actionable position of the viewer. The system can generate manipulation instructions to instruct the volumetric content playback system to manipulate the annotated volumetric content to achieve a desired emotional state of the viewer.

1 . A method comprising:
 creating, by a volumetric content enhancement system comprising a processor, an annotated volumetric video;   generating, by the volumetric content enhancement system, manipulation instructions to instruct a volumetric content playback system to manipulate the annotated volumetric video to achieve a desired emotional state of a viewer of the annotated volumetric video; and   providing, by the volumetric content enhancement system, the manipulation instructions to the volumetric content playback system.   
     
     
         2 . The method of  claim 1 , wherein the manipulation instructions are based, at least in part, upon viewer feedback provided by the viewer, a current emotional state of the viewer, and a position of the viewer. 
     
     
         3 . The method of  claim 2 , wherein the viewer feedback comprises explicit feedback provided by the viewer, passive feedback provided by at least one sensor monitoring the viewer, or the explicit feedback and the passive feedback. 
     
     
         4 . The method of  claim 1 , further comprising:
 receiving, by the volumetric content enhancement system, a volumetric video from a volumetric content capture system;   partitioning, by the volumetric content enhancement system, the volumetric video into a plurality of video frames;   analyzing, by the volumetric content enhancement system, the plurality of video frames to identify a plurality of voxels;   annotating, by the volumetric content enhancement system, at least a portion of the plurality of voxels with an annotation, wherein the annotation comprises contextual data about the portion of the plurality of voxels; and   determining, by the volumetric content enhancement system, at least one actionable position within the volumetric video.   
     
     
         5 . The method of  claim 4 , wherein the portion of the plurality of voxels comprises a region, and wherein the region identifies a character or an object depicted in the volumetric video. 
     
     
         6 . The method of  claim 1 , further comprising generating, by the volumetric content enhancement system, viewer guidance instructions to instruct the viewer to change from a current position to a different position. 
     
     
         7 . The method of  claim 1 , further comprising:
 obtaining, by the volumetric content enhancement system, new viewer feedback associated with the viewer; and   reassessing, by the volumetric content enhancement system, an emotional state of the viewer based, at least in part, on the new viewer feedback.   
     
     
         8 . A volumetric content enhancement system comprising:
 a processor; and   a memory comprising instructions that, when executed by the processor, cause the processor to perform operations comprising
 creating an annotated volumetric video, 
 generating manipulation instructions to instruct a volumetric content playback system to manipulate the annotated volumetric video to achieve a desired emotional state of a viewer of the annotated volumetric video, and 
 providing the manipulation instructions to the volumetric content playback system. 
   
     
     
         9 . The volumetric content enhancement system of  claim 8 , wherein the manipulation instructions are based, at least in part, upon viewer feedback provided by the viewer, a current emotional state of the viewer, and a position of the viewer. 
     
     
         10 . The volumetric content enhancement system of  claim 9 , wherein the viewer feedback comprises explicit feedback provided by the viewer, passive feedback provided by at least one sensor monitoring the viewer, or the explicit feedback and the passive feedback. 
     
     
         11 . The volumetric content enhancement system of  claim 8 , wherein the operations further comprise:
 receiving a volumetric video from a volumetric content capture system;   partitioning the volumetric video into a plurality of video frames;   analyzing the plurality of video frames to identify a plurality of voxels;   annotating at least a portion of the plurality of voxels with an annotation, wherein the annotation comprises contextual data about the portion of the plurality of voxels; and   determining at least one actionable position within the volumetric video.   
     
     
         12 . The volumetric content enhancement system of  claim 11 , wherein the portion of the plurality of voxels comprises a region, and wherein the region identifies a character or an object depicted in the volumetric video. 
     
     
         13 . The volumetric content enhancement system of  claim 11 , wherein the operations further comprise generating viewer guidance instructions to instruct the viewer to change from a specific actionable position to a different actionable position. 
     
     
         14 . The volumetric content enhancement system of  claim 8 , wherein the operations further comprise:
 obtaining new viewer feedback associated with the viewer; and   reassessing an emotional state of the viewer based, at least in part, on the new viewer feedback.   
     
     
         15 . A computer-readable storage medium comprising computer-executable instructions that, when executed by a processor, cause the processor to perform operations comprising:
 creating an annotated volumetric video;   generating manipulation instructions to instruct a volumetric content playback system to manipulate the annotated volumetric video to achieve a desired emotional state of a viewer of the annotated volumetric video; and   providing the manipulation instructions to the volumetric content playback system.   
     
     
         16 . The computer-readable storage medium of  claim 15 , wherein the manipulation instructions are based, at least in part, upon viewer feedback provided by the viewer, a current emotional state of the viewer, and a position of the viewer. 
     
     
         17 . The computer-readable storage medium of  claim 16 , wherein the viewer feedback comprises explicit feedback provided by the viewer, passive feedback provided by at least one sensor monitoring the viewer, or the explicit feedback and the passive feedback. 
     
     
         18 . The computer-readable storage medium of  claim 15 , wherein the operations further comprise:
 receiving a volumetric video from a volumetric content capture system;   partitioning the volumetric video into a plurality of video frames;   analyzing the plurality of video frames to identify a plurality of voxels;   annotating at least a portion of the plurality of voxels with an annotation, wherein the annotation comprises contextual data about the portion of the plurality of voxels; and   determining at least one actionable position within the volumetric video.   
     
     
         19 . The computer-readable storage medium of  claim 18 , wherein the portion of the plurality of voxels comprises a region, and wherein the region identifies a character or an object depicted in the volumetric video. 
     
     
         20 . The computer-readable storage medium of  claim 15 , wherein the operations further comprise:
 obtaining new viewer feedback associated with the viewer; and   reassessing an emotional state of the viewer based, at least in part, on the new viewer feedback.