Abstract: An automated method and system for generating modified digital video data finds locations of a visual marker image in a source video frame sequence and maps the location of the marker image in the frame sequence to create a tracking layer comprising data that tracks the location of the marker image in the source frame sequence. The tracking layer data maps the location of the marker image relative to the location of the marker image in a keyframe of the source video, the keyframe being a frame in which the match between the marker image and source video location has been detected with a relatively high confidence. An occlusion layer comprising alpha layer data can be created from the source video, the marker image, and the tracking layer to address frames in which features matching the marker image are occluded by foreground elements in the source video.

Abstract: System and computer-implemented method for editing a video sequence with temporal consistency. The method includes the steps of: computing a motion field modeling temporal consistency between successive frames; defining an energy functional modeling the desired properties to be enforced on the video sequence; splitting the video sequence into two sets with even frames and odd frames; computing the motion field between consecutive frames on the splitted sequences; recursively performing steps until the sets to be split contain one frame to edit; minimizing the energy functional for each set containing one frame to edit; merging the edited frames and outputting the edited video sequence.

Abstract: System and computer-implemented method for editing a video sequence with temporal consistency. The method includes the steps of: computing a motion field modeling temporal consistency between successive frames; defining an energy functional modeling the desired properties to be enforced on the video sequence; splitting the video sequence into two sets with even frames and odd frames; computing the motion field between consecutive frames on the splitted sequences; recursively performing steps until the sets to be split contain one frame to edit; minimizing the energy functional for each set containing one frame to edit; merging the edited frames and outputting the edited video sequence.