Composite video generation
Locations in which a person is depicted within video frames may be determined to identify portions of the video frames to be included in a composite video. A background image not including any depiction of the person may be generated, and the identified portions of the video frames may be inserted into the background image to generate the composite video.
1. A system for generating composite videos, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain video information defining a video having a progress length, the video including video frames, the video frames including depiction of a thing at different locations within the video frames;
select portions of the video frames to be included in a composite video based on the different locations of the depiction of the thing within the video frames;
generate a background image from the video frames, the background image not including the depiction of the thing; and
generate composite video frames of the composite video based on the selected portions of the video frames and the background image, the composite video frames including multiple depictions of the thing, wherein two or more of the selected portions of the video frames are combined into a single composite video frame based on different locations of a mask for the two or more of the selected portions of the video frames.
2. The system of claim 1 , wherein the background image is generated based on merging of two or more of the video frames.
3. The system of claim 1 , wherein the thing includes a living thing.
4. The system of claim 1 , wherein the thing includes a non-living thing.
5. The system of claim 1 , wherein the different locations of the mask include different placements and/or different sizes of the mask.
6. The system of claim 5 , wherein the different placements and/or the different sizes of the mask are determined to prevent overlap of the mask for the single composite video frame.
7. The system of claim 1 , wherein the video frames from which the selected portions are used to generate the composite video frames are selected based on matching of audio associated with the video frames.
8. The system of claim 1 , wherein the thing includes a person, and the video frames from which the selected portions are used to generate the composite video frames are selected based on matching of poses of the person depicted within the video frames.
9. A method for generating composite videos, the method performed by a computing system including one or more processors, the method comprising:
obtaining, by the computing system, video information defining a video having a progress length, the video including video frames, the video frames including depiction of a thing at different locations within the video frames;
selecting, by the computing system, portions of the video frames to be included in a composite video based on the different locations of the depiction of the thing within the video frames;
generating, by the computing system, a background image from the video frames, the background image not including the depiction of the thing; and
generating, by the computing system, composite video frames of the composite video based on the selected portions of the video frames and the background image, the composite video frames including multiple depictions of the thing, wherein two or more of the selected portions of the video frames are combined into a single composite video frame based on different locations of a mask for the two or more of the selected portions of the video frames.
10. The method of claim 9 , wherein the background image is generated based on merging of two or more of the video frames.
11. The method of claim 9 , wherein the thing includes a living thing.
12. The method of claim 9 , wherein the thing includes a non-living thing.
13. The method of claim 9 , wherein the different locations of the mask include different placements and/or different sizes of the mask.
14. The method of claim 13 , wherein the different placements and/or the different sizes of the mask are determined to prevent overlap of the mask for the single composite video frame.
15. The method of claim 9 , wherein the video frames from which the selected portions are used to generate the composite video frames are selected based on matching of audio associated with the video frames.
16. The method of claim 9 , wherein the thing includes a person and the video frames from which the selected portions are used to generate the composite video frames are selected based on matching of poses of the person depicted within the video frames.
17. A system for generating composite videos, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain video information defining a video having a progress length, the video including video frames, the video frames including depiction of a thing at different locations within the video frames;
select portions of the video frames to be included in a composite video based on the different locations of the depiction of the thing within the video frames;
generate a background image from the video frames based on merging of two or more of the video frames, the background image not including the depiction of the thing; and
generate composite video frames of the composite video based on the selected portions of the video frames and the background image, the composite video frames including multiple depictions of the thing, wherein two or more of the selected portions of the video frames are combined into a single composite video frame based on different locations of a mask for the two or more of the selected portions of the video frames, the different locations of the mask including different placements and/or different sizes of the mask.