Snap Angle Prediction for 360° Panoramas
Abstract
360° panoramas are a rich medium, yet notoriously difficult to visualize in the 2D image plane. We explore how intelligent rotations of a spherical image may enable content-aware projection with fewer perceptible distortions. Whereas existing approaches assume the viewpoint is fixed, intuitively some viewing angles within the sphere preserve high-level objects better than others. To discover the relationship between these optimal emph{snap angles} and the spherical panorama's content, we develop a reinforcement learning approach for the cubemap projection model. Implemented as a deep recurrent neural network, our method selects a sequence of rotation actions and receives reward for avoiding cube boundaries that overlap with important foreground objects. Our results demonstrate the impact both qualitatively and quantitatively.
Cite
Text
Xiong and Grauman. "Snap Angle Prediction for 360° Panoramas." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01228-1_1Markdown
[Xiong and Grauman. "Snap Angle Prediction for 360° Panoramas." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/xiong2018eccv-snap/) doi:10.1007/978-3-030-01228-1_1BibTeX
@inproceedings{xiong2018eccv-snap,
title = {{Snap Angle Prediction for 360° Panoramas}},
author = {Xiong, Bo and Grauman, Kristen},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01228-1_1},
url = {https://mlanthology.org/eccv/2018/xiong2018eccv-snap/}
}