Systems and methods for framing videos
A video may include a capture of a scene, such as a wide-field of view capture of the scene. A punchout of the video may provide a framing of the captured scene. The punchout may be determined based on the context of the video, such as the type of captured scene within the video, the motion of the image capture device that captured the video, and/or the motion of one or more things within the captured scene.
1. A system for framing videos, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain video information defining a video, the video including video content having a progress length, the video content including visual content viewable as a function of progress through the progress length, the visual content having a field of view;
assess context of the video content as the function of progress through the progress length as being of an action type, a setting type, or a social type, wherein different context of the video content are associated with different criteria for determining a viewing window for the visual content;
determine the viewing window for the visual content as the function of progress through the progress length based on the context of the video content, wherein the viewing window is determined based on a first criteria based on the context of the video content being of the action type, the viewing window is determined based on a second criteria based on the context of the video content being of the setting type, and the viewing window is determined based on a third criteria based on the context of the video content being of the social type, the first criteria different from the second criteria and the third criteria, and the second criteria different from the third criteria, the viewing window defining extents of the visual content to be included within framed visual content, wherein the determination of the viewing window based on the third criteria associated with the social type includes placement of the viewing window within the visual content to provide a selfie-view of a person or a perspective-view of the person, wherein the perspective view of the person is determined based on gaze of the person within the selfie-view of the person; and
generate the framed visual content based on the viewing window, the framed visual content including the extents of the visual content within the viewing window.
2. The system of claim 1 , wherein the determination of the viewing window based on the first criteria associated with the action type includes movement of the viewing window within the visual content to follow an action captured within the visual content.
3. The system of claim 1 , wherein the determination of the viewing window based on the first criteria associated with the action type includes a change in projection of the visual content based on motion of a thing depicted within the visual content.
4. The system of claim 3 , wherein the change in the projection of the visual content based on the motion of the thing depicted within the visual content includes a switch between a non-stereographic projection and a stereographic projection based on the motion of the thing including the thing jumping or the thing being thrown.
5. The system of claim 1 , wherein the determination of the viewing window based on the second criteria associated with the setting type includes movement of the viewing window within the visual content to provide a panning view of a scenery captured within the visual content.
6. The system of claim 1 , wherein the determination of the viewing window based on the third criteria associated with the social type further includes movement of the viewing window within the visual content to provide a panning view of different individuals captured within the visual content.
7. The system of claim 1 , wherein the determination of the viewing window based on the third criteria associated with the social type further includes change in placement of the viewing window within the visual content to provide a switching view of different individuals captured within the visual content.
8. A method for framing 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, the video including video content having a progress length, the video content including visual content viewable as a function of progress through the progress length, the visual content having a field of view;
assessing, by the computing system, context of the video content as the function of progress through the progress length as being of an action type, a setting type, or a social type, wherein different context of the video content are associated with different criteria for determining a viewing window for the visual content;
determining, by the computing system, the viewing window for the visual content as the function of progress through the progress length based on the context of the video content, wherein the viewing window is determined based on a first criteria based on the context of the video content being of the action type, the viewing window is determined based on a second criteria based on the context of the video content being of the setting type, and the viewing window is determined based on a third criteria based on the context of the video content being of the social type, the first criteria different from the second criteria and the third criteria, and the second criteria different from the third criteria, the viewing window defining extents of the visual content to be included within framed visual content, wherein determining the viewing window based on the third criteria associated with the social type includes placing the viewing window within the visual content to provide a selfie-view of a person or a perspective-view of the person, wherein the perspective view of the person is determined based on gaze of the person within the selfie-view of the person; and
generating, by the computing system, the framed visual content based on the viewing window, the framed visual content including the extents of the visual content within the viewing window.
9. The method of claim 8 , wherein determining the viewing window based on the first criteria associated with the action type includes moving the viewing window within the visual content to follow an action captured within the visual content.
10. The method of claim 8 , wherein determining the viewing window based on the first criteria associated with the action type includes changing projection of the visual content based on motion of a thing depicted within the visual content.
11. The method of claim 10 , wherein the change in the projection of the visual content based on the motion of the thing depicted within the visual content includes a switch between a non-stereographic projection and a stereographic projection based on the motion of the thing including the thing jumping or the thing being thrown.
12. The method of claim 8 , wherein determining the viewing window based on the second criteria associated with the setting type includes moving the viewing window within the visual content to provide a panning view of a scenery captured within the visual content.
13. The method of claim 8 , wherein determining the viewing window based on the third criteria associated with the social type further includes moving the viewing window within the visual content to provide a panning view of different individuals captured within the visual content.
14. The method of claim 8 , wherein determining the viewing window based on the third criteria associated with the social type further includes changing placement of the viewing window within the visual content to provide a switching view of different individuals captured within the visual content.
15. A system for framing videos, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain video information defining a video, the video including video content having a progress length, the video content including visual content viewable as a function of progress through the progress length, the visual content having a field of view;
assess context of the video content as the function of progress through the progress length as being of an action type, a setting type, or a social type, wherein different context of the video content are associated with different criteria for determining a viewing window for the visual content;
determine the viewing window for the visual content as the function of progress through the progress length based on the context of the video content, wherein the viewing window is determined based on a first criteria based on the context of the video content being of the action type, the viewing window is determined based on a second criteria based on the context of the video content being of the setting type, and the viewing window is determined based on a third criteria based on the context of the video content being of the social type, the first criteria different from the second criteria and the third criteria, and the second criteria different from the third criteria, the viewing window defining extents of the visual content to be included within framed visual content, further wherein;
the determination of the viewing window based on the first criteria associated with the action type includes movement of the viewing window within the visual content to follow an action captured within the visual content;
the determination of the viewing window based on the second criteria associated with the setting type includes movement of the viewing window within the visual content to provide a panning view of a scenery captured within the visual content; and
the determination of the viewing window based on the third criteria associated with the social type includes placement of the viewing window within the visual content to provide a selfie-view of a person or a perspective-view of the person, wherein the perspective view of the person is determined based on gaze of the person within the selfie-view of the person; and
generate the framed visual content based on the viewing window, the framed visual content including the extents of the visual content within the viewing window.
16. The system of claim 15 , wherein, the determination of the viewing window based on the third criteria associated with the social type further includes:
movement of the viewing window within the visual content to provide a panning view of different individuals captured within the visual content; or
change in placement of the viewing window within the visual content to provide a switching view of different individuals captured within the visual content.