Estimating Natural Illumination from a Single Outdoor Image
| Jean-François Lalonde | Alexei A. Efros | Srinivasa G. Narasimhan |
IEEE International Conference on Computer Vision (2009)
Given a single outdoor image, we present a method for estimating the likely illumination conditions of the scene. In particular, we compute the probability distribution over the sun position and visibility. The method relies on a combination of weak cues that can be extracted from different portions of the image: the sky, the vertical surfaces, and the ground. While no single cue can reliably estimate illumination by itself, each one can reinforce the others to yield a more robust estimate. This is combined with a data-driven prior computed over a dataset of 6 million Internet photos. We present quantitative results on a webcam dataset with annotated sun positions, as well as qualitative results on consumer- grade photographs downloaded from Internet. Based on the estimated illumination, we show how to realistically insert synthetic 3-D objects into the scene.
Jean-François Lalonde, Alexei A. Efros, Srinivasa G. Narasimhan (2009). Estimating Natural Illumination from a Single Outdoor Image. IEEE International Conference on Computer Vision.
@inproceedings{lalonde-iccv-09,
Author = "Jean-Fran\c{c}ois Lalonde and Alexei A. Efros and Srinivasa G. Narasimhan",
Booktitle = "IEEE International Conference on Computer Vision",
Title = "Estimating Natural Illumination from a Single Outdoor Image",
Year = "2009",
Abstract = {Given a single outdoor image, we present a method for estimating the likely illumination conditions of the scene. In particular, we compute the probability distribution over the sun position and visibility. The method relies on a combination of weak cues that can be extracted from different portions of the image: the sky, the vertical surfaces, and the ground. While no single cue can reliably estimate illumination by itself, each one can reinforce the others to yield a more robust estimate. This is combined with a data-driven prior computed over a dataset of 6 million Internet photos. We present quantitative results on a webcam dataset with annotated sun positions, as well as qualitative results on consumer- grade photographs downloaded from Internet. Based on the estimated illumination, we show how to realistically insert synthetic 3-D objects into the scene. },
}
