Reasoning about Photo Collections using Models of Outdoor Illumination
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.78
Abstract
Natural illumination from the sun and sky plays a significant role in the appearance of outdoor scenes. We introduce the use of sophisticated outdoor illumination models, developed in the computer graphics community, for estimating the appearance of an outdoor scene and timestamps from a large set of uncalibrated images. We first present an analysis of the relationship between these illumination models and the geolocation, time, surface orientation, and local visibility at a scene point. We then use this relationship to devise a data-driven method for estimating per-point albedo and local visibility information from a set of Internet photos taken under varying, unknown illuminations. Our approach significantly extends prior work on appearance estimation to work with sun-sky models, and enables new applications, such as computing timestamps for individual photos using shading information.
Session
Poster Session
Files
Citation
Daniel Hauagge, Scott Wehrwein, Paul Upchurch, Kavita Bala, and Noah Snavely. Reasoning about Photo Collections using Models of Outdoor Illumination. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.78
title = {Reasoning about Photo Collections using Models of Outdoor Illumination},
author = {Hauagge, Daniel and Wehrwein, Scott and Upchurch, Paul and Bala, Kavita and Snavely, Noah},
year = {2014},
booktitle = {Proceedings of the British Machine Vision Conference},
publisher = {BMVA Press},
editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
doi = { http://dx.doi.org/10.5244/C.28.78 }
}