Title
Semantic-Driven Generation of Hyperlapse from 360 Degree Video.
Abstract
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 d...
Year
DOI
Venue
2018
10.1109/TVCG.2017.2750671
IEEE Transactions on Visualization and Computer Graphics
Keywords
Field
DocType
Cameras,Semantics,Two dimensional displays,Visualization,Three-dimensional displays,Computational modeling,Rendering (computer graphics)
Computer vision,Computer science,Visualization,Salience (neuroscience),Spacetime,Image stabilization,Exploit,Smoothing,Artificial intelligence,Smoothness,Semantics
Journal
Volume
Issue
ISSN
24
9
1077-2626
Citations 
PageRank 
References 
14
0.55
21
Authors
6
Name
Order
Citations
PageRank
Wei-Sheng Lai116412.87
Yujia Huang2140.89
Neel Joshi3115563.95
Christopher James Buehler4140.55
Yang Ming-Hsuan515303620.69
Sing Bing Kang65064345.13