GAZED- Gaze-guided Cinematic Editing of Wide-Angle Monocular Video Recordings
This work addresses the challenge of automated video editing for users capturing wide-angle footage, though it appears incremental as it builds on existing gaze-based methods.
The authors tackled the problem of automatically editing wide-angle monocular videos into cinematic sequences by using eye-gaze tracks as a proxy for shot selection, resulting in an edited video that was evaluated through a psychophysical study with 12 users and 12 performance videos.
We present GAZED- eye GAZe-guided EDiting for videos captured by a solitary, static, wide-angle and high-resolution camera. Eye-gaze has been effectively employed in computational applications as a cue to capture interesting scene content; we employ gaze as a proxy to select shots for inclusion in the edited video. Given the original video, scene content and user eye-gaze tracks are combined to generate an edited video comprising cinematically valid actor shots and shot transitions to generate an aesthetic and vivid representation of the original narrative. We model cinematic video editing as an energy minimization problem over shot selection, whose constraints capture cinematographic editing conventions. Gazed scene locations primarily determine the shots constituting the edited video. Effectiveness of GAZED against multiple competing methods is demonstrated via a psychophysical study involving 12 users and twelve performance videos.