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

要旨

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.

キーワード
Eye gaze
Cinematic video editing
Stage performance
Static wide-angle recording
Gaze potential
Shot selection
Dynamic programming
著者
K. L. Bhanu Moorthy
International Institute of Information Technology, Hyderabad, Hyderabad, India
Moneish Kumar
Samsung R&D Institute Bangalore, Bangalore, India
Ramanathan Subramanian
Indian Institute of Technology Ropar, Ropar, India
Vineet Gandhi
International Institute of Information Technology, Hyderabad, Hyderabad, India
DOI

10.1145/3313831.3376544

論文URL

https://doi.org/10.1145/3313831.3376544

動画

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: Photo & video manipulation

Paper session
312 NI'IHAU
5 件の発表
2020-04-28 23:00:00
2020-04-29 00:15:00
日本語まとめ
読み込み中…