Techniques for adding interactive features to videos

摘要

Techniques are disclosed for adding interactive features to videos to enable users to create new media using a dynamic blend of motion and still imagery. The interactive techniques can include allowing a user to change the starting time of one or more subjects in a given video frame, or only animate/play a portion of a given frame scene. The techniques may include segmenting each frame of a video to identify one or more subjects within each frame, selecting (or receiving selections of) one or more subjects within the given frame scene, tracking the selected subject(s) from frame to frame, and alpha-matting to play/animate only the selected subject(s). In some instances, segmentation, selection, and/or tracking may be improved and/or enhanced using pixel depth information (e.g., using a depth map).

主权项

1. A method comprising:
segmenting each frame of a video into its semantic components to identify one or more subjects within each frame scene based on a respective group of pixels, wherein the video is a part of media; receiving a selection of one or more subjects within a given frame scene; tracking the one or more subjects from frame to frame of the video to identify the respective group of pixels comprising the one or more subjects in each frame; and alpha-matting the media to isolate the one or more selected subjects from frame to frame.