Making 360$^{\circ}$ Video Watchable in 2D: Learning Videography for Click Free Viewing
This addresses the suboptimal viewing experience for users of 360° video by enabling click-free viewing, though it is incremental as it builds on virtual cinematography with a novel method.
The paper tackles the problem of making 360° video watchable in 2D by automatically controlling a virtual camera to reduce viewer burden, achieving more general camera control and substantially improved efficiency compared to state-of-the-art methods, as validated on over 7 hours of real video.
360$^{\circ}$ video requires human viewers to actively control "where" to look while watching the video. Although it provides a more immersive experience of the visual content, it also introduces additional burden for viewers; awkward interfaces to navigate the video lead to suboptimal viewing experiences. Virtual cinematography is an appealing direction to remedy these problems, but conventional methods are limited to virtual environments or rely on hand-crafted heuristics. We propose a new algorithm for virtual cinematography that automatically controls a virtual camera within a 360$^{\circ}$ video. Compared to the state of the art, our algorithm allows more general camera control, avoids redundant outputs, and extracts its output videos substantially more efficiently. Experimental results on over 7 hours of real "in the wild" video show that our generalized camera control is crucial for viewing 360$^{\circ}$ video, while the proposed efficient algorithm is essential for making the generalized control computationally tractable.