GAZED- Gaze-guided Cinematic Editing of Wide-Angle Monocular Video Recordings

摘要: 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 cue to capture interesting scene content; we employ gaze proxy select shots inclusion the edited video. Given original video, content user eye-gaze tracks are combined generate an video comprising cinematically valid actor shot transitions aesthetic vivid representation of narrative. model cinematic editing energy minimization problem over selection, whose constraints cinematographic conventions. Gazed locations primarily determine constituting Effectiveness GAZED against multiple competing methods is demonstrated via psychophysical study involving 12 users twelve performance videos.