A Dataset of Flash and Ambient Illumination Pairs from the Crowd
Name
fai.pdf
Description
Accepted version
Size
4.13 MB
Format
Adobe PDF
Checksum (MD5)
0e40f0be3c2c0a843d8cccbced745200
Author(s)
Aksoy, Yagiz
Kim, Changil
Kellnhofer, Petr
Paris, Sylvain
Elgharib, Mohamed
Pollefeys, Marc
Matusik, Wojciech
Date Issued
2018
Journal
European Conference on Computer Vision
Publisher
Springer International Publishing
Citation
Aksoy, Yagiz et al. "A Dataset of Flash and Ambient Illumination Pairs from the Crowd." European Conference on Computer Vision, September 2018, Munich, Germany, Springer, 2018 © 2018 Springer International Publishing
Version
Author's final manuscript
Abstract
Illumination is a critical element of photography and is essential for many computer vision tasks. Flash light is unique in the sense that it is a widely available tool for easily manipulating the scene illumination. We present a dataset of thousands of ambient and flash illumination pairs to enable studying flash photography and other applications that can benefit from having separate illuminations. Different than the typical use of crowdsourcing in generating computer vision datasets, we make use of the crowd to directly take the photographs that make up our dataset. As a result, our dataset covers a wide variety of scenes captured by many casual photographers. We detail the advantages and challenges of our approach to crowdsourcing as well as the computational effort to generate completely separate flash illuminations from the ambient light in an uncontrolled setup. We present a brief examination of illumination decomposition, a challenging and underconstrained problem in flash photography, to demonstrate the use of our dataset in a data-driven approach. Keywords: Flash photography; Dataset collection; Crowdsourcing; Illumination decomposition
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-01240-3_39
