Shadow Detection and Sun Direction in Photo Collections
Scott Wehrwein, Kavita Bala, Noah Snavely
 |
| Modeling the appearance of outdoor scenes from photo collections is challenging because of appearance variation, especially due to illumination. In this paper we present a simple and robust algorithm for estimating illumination properties - shadows and sun direction - from photo collections. These properties are key to a variety of scene modeling applications, including outdoor intrinsic images, realistic 3D scene rendering, and temporally varying (4D) reconstruction. Our shadow detection method uses illumination ratios to analyze lighting independent of camera effects, and determines shadow labels for each 3D point in a reconstruction. These shadow labels can then be used to detect shadow boundaries and estimate sun direction, as well as to compute dense shadow labels in pixel space. We demonstrate our method on large Internet photo collections of scenes, and show that it outperforms prior multi-image shadow detection and sun direction estimation methods. |
Notes and Updates
- 2015-11-04: Slides and poster are now available for download below. Code is coming soon - if you're interested, send Scott an email to be notified when it's released.
- 2015-08-31: The paper will be presented as an oral at 3DV 2015 in Lyon, France.
Related Projects
- Our work on estimating outdoor illumination using related intensity statistics.
- Our original work on Photometric Ambient Occlusion.
Downloads
|
|
|
|
BibTeX entry
@inproceedings{wehrwein_2015_shadows,Title = {Shadow Detection and Sun Direction in Photo Collections},
Author = {Scott Wehrwein and Kavita Bala and Noah Snavely},
booktitle = {Proceedings of 3DV},
Year = {2015}
}
Acknowledgments.This work was supported in part by grants from the NSF (IIS-1111534), Amazon AWS for Education, Google, and the Intel Science and Technology Center for Visual Computing. The authors thank Paul Upchurch and Daniel Hauagge for their help with figures, and Joe Kider for assistance in capturing the Tentacle dataset.