Systems and methods for dynamically stabilizing videos
A video may be captured by an image capture device. A stabilized view of the video may be generated by using a punchout of the video. The shape and/or size of the punchout may be dynamically changed based on stabilization performance of the video. The shape and/or size of the punchout may be changed when the punchout is moving within the video. The shape and/or size of the punchout may not be changed when the punchout is not moving within the video.
1. A system for dynamically stabilizing 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 captured by an image capture device during a capture duration, the visual content having a field of view;
determine stabilization performance of the visual content using a punchout of the visual content within a viewing window;
determine movement of the viewing window for the punchout of the visual content within the field of view of the visual content, the movement of the viewing window for the punchout of the visual content within the field of view of the visual content including a change in placement of the viewing window within the field of view of the visual content between different video frames of the video; and
stabilize the visual content using a dynamic punchout of the visual content, the dynamic punchout of the visual content including a dynamic change in the viewing window for the punchout of the visual content based on the stabilization performance of the visual content using the punchout of the visual content within the viewing window and the movement of the viewing window for the punchout of the visual content within the field of view of the visual content, the dynamic change in the viewing window includes a change in shape and/or size of the viewing window.
2. The system of claim 1 , wherein the stabilization performance of the visual content using the punchout of the visual content within the viewing window includes a number of times the stabilization requires the viewing window to extend beyond the field of view of the visual content and/or an amount of stabilization margin between the viewing window and the field of view of the visual content.
3. A system for dynamically stabilizing 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 captured by an image capture device during a capture duration, the visual content having a field of view;
determine stabilization performance of the visual content using a punchout of the visual content within a viewing window;
determine movement of the viewing window for the punchout of the visual content within the field of view of the visual content; and
stabilize the visual content using a dynamic punchout of the visual content, the dynamic punchout of the visual content including a dynamic change in the viewing window for the punchout of the visual content based on the stabilization performance of the visual content using the punchout of the visual content within the viewing window and the movement of the viewing window for the punchout of the visual content within the field of view of the visual content.
4. The system of claim 3 , wherein the stabilization performance of the visual content using the punchout of the visual content within the viewing window includes a number of times the stabilization requires the viewing window to extend beyond the field of view of the visual content.
5. The system of claim 3 , wherein the stabilization performance of the visual content using the punchout of the visual content within the viewing window includes an amount of stabilization margin between the viewing window and the field of view of the visual content.
6. The system of claim 3 , wherein the movement of the viewing window for the punchout of the visual content within the field of view of the visual content includes a change in placement of the viewing window within the field of view of the visual content between different video frames of the video.
7. The system of claim 3 , wherein the dynamic change in the viewing window includes a change in shape and/or size of the viewing window.
8. The system of claim 3 , wherein the dynamic change in the viewing window includes switching between a first viewing window and a second viewing window different from the first viewing window, the first viewing window determined based on user selection, the second viewing window determined based on the user selection of the first viewing window.
9. The system of claim 3 , wherein the dynamic change in the viewing window includes a successive change through three or more different viewing windows.
10. The system of claim 3 , wherein responsive to the stabilization performance of the visual content using the punchout of the visual content within the viewing window indicating that the stabilization is possible using a larger and/or wider viewing window:
the dynamic change in the viewing window includes a change to the larger and/or wider viewing window based on the movement of the viewing window for the punchout of the visual content within the field of view of the visual content including the viewing window moving more than a threshold amount; and
the dynamic change in the viewing window does not include the change to the larger and/or wider viewing window based on the movement of the viewing window for the punchout of the visual content within the field of view of the visual content including the viewing window not moving more than the threshold amount.
11. The system of claim 3 , wherein the dynamic change in the viewing window and the stabilization of the visual content using the dynamic punchout of the visual content are performed by the image capture device during capture of the visual content.
12. A method for dynamically stabilizing 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 captured by an image capture device during a capture duration, the visual content having a field of view;
determining, by the computing system, stabilization performance of the visual content using a punchout of the visual content within a viewing window;
determining, by the computing system, movement of the viewing window for the punchout of the visual content within the field of view of the visual content; and
stabilizing, by the computing system, the visual content using a dynamic punchout of the visual content, the dynamic punchout of the visual content including a dynamic change in the viewing window for the punchout of the visual content based on the stabilization performance of the visual content using the punchout of the visual content within the viewing window and the movement of the viewing window for the punchout of the visual content within the field of view of the visual content.
13. The method of claim 12 , wherein the stabilization performance of the visual content using the punchout of the visual content within the viewing window includes a number of times the stabilization requires the viewing window to extend beyond the field of view of the visual content.
14. The method of claim 12 , wherein the stabilization performance of the visual content using the punchout of the visual content within the viewing window includes an amount of stabilization margin between the viewing window and the field of view of the visual content.
15. The method of claim 12 , wherein the movement of the viewing window for the punchout of the visual content within the field of view of the visual content includes a change in placement of the viewing window within the field of view of the visual content between different video frames of the video.
16. The method of claim 12 , wherein the dynamic change in the viewing window includes a change in shape and/or size of the viewing window.
17. The method of claim 12 , wherein the dynamic change in the viewing window includes switching between a first viewing window and a second viewing window different from the first viewing window, the first viewing window determined based on user selection, the second viewing window determined based on the user selection of the first viewing window.
18. The method of claim 12 , wherein the dynamic change in the viewing window includes a successive change through three or more different viewing windows.
19. The method of claim 12 , wherein responsive to the stabilization performance of the visual content using the punchout of the visual content within the viewing window indicating that the stabilization is possible using a larger and/or wider viewing window:
the dynamic change in the viewing window includes a change to the larger and/or wider viewing window based on the movement of the viewing window for the punchout of the visual content within the field of view of the visual content including the viewing window moving more than a threshold amount; and
the dynamic change in the viewing window does not include the change to the larger and/or wider viewing window based on the movement of the viewing window for the punchout of the visual content within the field of view of the visual content including the viewing window not moving more than the threshold amount.
20. The method of claim 12 , wherein the dynamic change in the viewing window and the stabilization of the visual content using the dynamic punchout of the visual content are performed by the image capture device during capture of the visual content.