Robust Upright Adjustment of 360 Spherical Panoramas

Jinwoong Jung
POSTECH

Beomseok Kim
POSTECH

Joon-Young Lee
Adobe Research

Byoungmoon Kim
Adobe Research

Seungyong Lee
POSTECH

The Visual Computer (Special Issue on CGI 2017), Vol. 33, No. 6-8, May 2017



(a) Input Image

(b) Our Result


Abstract

With the recent advent of 360 cameras, spherical panorama images are becoming more popular and widely available. In a spherical panorama, alignment of the scene orientation to the image axes is important for providing comfortable and pleasant viewing experiences using VR headsets and traditional displays. This paper presents an automatic method for upright adjustment of 360 spherical panorama images without any prior information, such as depths and Gyro sensor data. We take the Atlanta world assumption and use the horizontal and vertical lines in the scene to formulate a cost function for upright adjustment. In addition to fast optimization of the cost function, our method includes outlier handling to improve the robustness and accuracy of upright adjustment. Our method produces visually pleasing results for a variety of real-world spherical panoramas in less than a second and the accuracy is verified using ground-truth data.


Paper
PDF, 15.0MB
Talk
PPT, 22.4MB
see the new features in coupe website [link]

BibTex

@article{jung2017robust,
title={Robust upright adjustment of 360 spherical panoramas},
author={Jung, Jinwoong and Kim, Beomseok and Lee, Joon-Young and Kim, Byungmoon and Lee, Seungyong},
journal={The Visual Computer},
pages={1--11},
year={2017},
publisher={Springer}
}