Volumetric data post-production and distribution system
Various post-production and distribution tools for volumetric video data are enabled. For instance, a method comprises receiving, by a device comprising a processor, a group of images, determining, by the device, first points of interest of a first image of the group of images and second points of interest of a second image of the group of images, comparing, by the device, the first points of interest to the second points of interest, and determining, by the device, from the first points of interest and the second points of interest and based on a result of the comparing, sets of candidate coordinate positions of a joint of a character represented in the first image and the second image.
1. A method, comprising:
comparing, by a device comprising a processor, a first frame of a video to a second frame of the video, wherein the video is a first version of the video from multiple versions of the video;
based on the comparing, determining, by the device, a set of three-dimensional points defining a position of a joint of a character represented in the video; and
in response to receiving an edit that adjusts the position of the joint in the first version of the video, concurrently making, by the device, respective corresponding adjustments to the position of the joint in one or more second versions of the video from the multiple versions of the video different than the first version.
2. The method of claim 1 , wherein the first frame is captured from a first vantage point applicable to a scene in which the character is represented, and the second frame is captured from a second vantage point applicable to the scene.
3. The method of claim 1 , wherein the concurrently making the respective corresponding adjustments to the position of the joint in the one or more second versions of the video comprises varying a corresponding adjustment of the respective corresponding adjustments of the position of the joint in at least one of the one or more second versions of the video.
4. The method of claim 1 , further comprising:
in response to receiving another edit that adjusts a rotation of the joint in the first version of the video, concurrently making, by the device, respective corresponding adjustments to the rotation of the joint in the one or more second versions of the video.
5. The method of claim 4 , wherein the concurrently making the respective corresponding adjustments to the rotation of the joint in the one or more second versions of the video, comprises varying a corresponding adjustment of the rotation of the joint in at least one of the one or more second versions of the video.
6. The method of claim 1 , further comprising, generating, by the device, a skeletal rig comprising the joint based on the set of three-dimensional points.
7. The method of claim 1 , wherein the video is a volumetric video generated from two-dimensional videos.
8. A system, comprising:
a processor; and
a memory communicatively coupled to the processor, the memory having stored therein computer-executable instructions, comprising:
an edit unit that:
compares a first frame of a video to a second frame of the video, wherein the video is a first version of the video from multiple versions of the video, and the edit unit;
based on the comparing, determines a group of three-dimensional points defining a position of a joint of a character represented in the video;
in response to receiving an edit that adjusts a rotation of the joint in the first version of the video, concurrently performs respective corresponding adjustments to the rotation of the joint in one or more second versions of the video from the multiple versions of the video different than the first version.
9. The system of claim 8 , wherein the first frame is captured from a first perspective to a scene in which the character is represented, and the second frame is captured from a second perspective to the scene different than the first perspective.
10. The system of claim 8 , wherein the edit unit, in response to receiving another edit that adjusts the position of the joint in the first version of the video, concurrently performs respective corresponding adjustments to the position of the joint in the one or more second versions of the video.
11. The system of claim 10 , wherein the edit unit further varies a corresponding adjustment of the position of the joint in at least one of the one or more second versions of the video.
12. The system of claim 8 , wherein the edit unit generates a skeletal rig comprising the joint based on the group of three-dimensional points.
13. The system of claim 8 , wherein the video is a volumetric video generated from two-dimensional videos.
14. The system of claim 8 , wherein the edit unit further varies a corresponding adjustment of the rotation of the joint in at least one of the one or more second versions of the video.
15. A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
comparing a first frame of a video to a second frame of the video, wherein the video is a first version of the video from multiple versions of the video;
based on the comparing, determining three-dimensional points defining a position of a joint of a character represented in the video; and
in response to receiving an edit that adjusts the position of the joint in the first version of the video, concurrently generating respective corresponding adjustments to the position of the joint in one or more second versions of the video from the multiple versions of the video different than the first version.
16. The non-transitory machine-readable medium of claim 15 , wherein the first frame is captured from a first vantage point applicable to a scene in which the character is represented, and the second frame is captured from a second vantage point applicable to the scene.
17. The non-transitory machine-readable medium of claim 15 , wherein the concurrently generating the respective corresponding adjustments to the position of the joint in the one or more second versions of the video, comprises varying a corresponding adjustment of the position of the joint in at least one of the one or more second versions of the video.
18. The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise:
in response to receiving another edit that adjusts a rotation of the joint in the first version of the video, concurrently generating respective corresponding adjustments to the rotation of the joint in second versions of the video from the multiple versions of the video different than the first version.
19. The non-transitory machine-readable medium of claim 18 , wherein the concurrently generating the respective corresponding adjustments to the rotation of the joint in the second versions of the video, comprises varying a corresponding adjustment of the rotation of the joint in at least one of the second versions of the video.
20. The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise generating a skeletal rig comprising the joint based on the three-dimensional points.