ML Anthology

Using Cloud Shadows to Infer Scene Structure and Camera Calibration

Nathan Jacobs, Brian Bies, Robert Pless
CVPR 2010 pp. 1102-1109
doi:10.1109/CVPR.2010.5540093 /cvpr/2010/jacobs2010cvpr-using/

Abstract

We explore the use of clouds as a form of structured lighting to capture the 3D structure of outdoor scenes observed over time from a static camera. We derive two cues that relate 3D distances to changes in pixel intensity due to clouds shadows. The first cue is primarily spatial, works with low frame-rate time lapses, and supports estimating focal length and scene structure, up to a scale ambiguity. The second cue depends on cloud motion and has a more complex, but still linear, ambiguity. We describe a method that uses the spatial cue to estimate a depth map and a method that combines both cues. Results on time lapses of several outdoor scenes show that these cues enable estimating scene geometry and camera focal length.

CVPR Semantic Scholar

Cite

Text

Jacobs et al. "Using Cloud Shadows to Infer Scene Structure and Camera Calibration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540093

Markdown

[Jacobs et al. "Using Cloud Shadows to Infer Scene Structure and Camera Calibration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/jacobs2010cvpr-using/) doi:10.1109/CVPR.2010.5540093

BibTeX

@inproceedings{jacobs2010cvpr-using,
  title     = {{Using Cloud Shadows to Infer Scene Structure and Camera Calibration}},
  author    = {Jacobs, Nathan and Bies, Brian and Pless, Robert},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {1102-1109},
  doi       = {10.1109/CVPR.2010.5540093},
  url       = {https://mlanthology.org/cvpr/2010/jacobs2010cvpr-using/}
}