Semantic-driven Generation of Hyperlapse from $360^\circ$ Video
This addresses the challenge of creating optimal viewing experiences from panoramic videos for users, though it is incremental as it builds on existing hyperlapse and stabilization techniques.
The paper tackles the problem of converting 360° video into normal field-of-view hyperlapses by using visual saliency and semantics for non-uniform spatiotemporal sampling, with results validated through a user study against state-of-the-art methods.
We present a system for converting a fully panoramic ($360^\circ$) video into a normal field-of-view (NFOV) hyperlapse for an optimal viewing experience. Our system exploits visual saliency and semantics to non-uniformly sample in space and time for generating hyperlapses. In addition, users can optionally choose objects of interest for customizing the hyperlapses. We first stabilize an input $360^\circ$ video by smoothing the rotation between adjacent frames and then compute regions of interest and saliency scores. An initial hyperlapse is generated by optimizing the saliency and motion smoothness followed by the saliency-aware frame selection. We further smooth the result using an efficient 2D video stabilization approach that adaptively selects the motion model to generate the final hyperlapse. We validate the design of our system by showing results for a variety of scenes and comparing against the state-of-the-art method through a user study.