arxivst stuff from arxiv that you should probably bookmark

Semantic-driven Generation of Hyperlapse from 360 degree Video

Abstract · Mar 31, 2017 08:42 ·

cs-cv

Arxiv Abstract

  • Wei-Sheng Lai
  • Yujia Huang
  • Neel Joshi
  • Chris Buehler
  • Ming-Hsuan Yang
  • Sing Bing Kang

We present a system for converting a fully panoramic (360 degree) 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 degree 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.

Read the paper (pdf) »