Pano2Vid: Automatic Cinematography for Watching 360° Videos
Loading...
Date
2017
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We introduce the novel task of Pano2Vid --- automatic cinematography in panoramic 360° videos. Given a 360° video, the goal is to direct an imaginary camera to virtually capture natural-looking normal field-of-view (NFOV) video. By selecting "where to look" within the panorama at each time step, Pano2Vid aims to free both the videographer and the end viewer from the task of determining what to watch. Towards this goal, we first compile a dataset of 360° videos downloaded from the web, together with human-edited NFOV camera trajectories to facilitate evaluation. Next, we propose AutoCam, a data-driven approach to solve the Pano2Vid task. AutoCam leverages NFOV web video to discriminatively identify space-time "glimpses" of interest at each time instant, and then uses dynamic programming to select optimal human-like camera trajectories. Through experimental evaluation on multiple newly defined Pano2Vid performance measures against several baselines, we show that our method successfully produces informative videos that could conceivably have been captured by human videographers.
Description
@inproceedings{10.2312:wiced.20171071,
booktitle = {Eurographics Workshop on Intelligent Cinematography and Editing},
editor = {William Bares and Vineet Gandhi and Quentin Galvane and Remi Ronfard},
title = {{Pano2Vid: Automatic Cinematography for Watching 360° Videos}},
author = {Su, Yu-Chuan and Jayaraman, Dinesh and Grauman, Kristen},
year = {2017},
publisher = {The Eurographics Association},
ISSN = {2411-9733},
ISBN = {978-3-03868-031-4},
DOI = {10.2312/wiced.20171071}
}