Estimating Natural Illumination
from a Single Outdoor Image
|From a single image (left), we estimate the most likely sky appearance (middle) and insert a 3-D object (right). Illumination estimation was done entirely automatically.|
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, the ground, and the convex objects in the image. 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 photos. We present quantitative results on a webcam dataset with annotated sun positions, as well as quantitative and 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, and how to transfer appearance across images while keeping the illumination consistent.
Citation - IJCV 2012
|Jean-François Lalonde, Alexei A. Efros, and Srinivasa G. Narasimhan. Estimating the Natural Illumination Conditions from a Single Outdoor Image, International Journal on Computer Vision, 98(2):123-145, 2012. [PDF pre-print] [BibTeX]|
Citation - ICCV 2009
|Jean-François Lalonde, Alexei A. Efros, and Srinivasa G. Narasimhan. Estimating Natural Illumination from a Single Outdoor Image, International Conference on Computer Vision, 2009. [PDF] [BibTeX]|
Poster - ICCP 2011
|Jean-François Lalonde, Alexei A. Efros, and Srinivasa G. Narasimhan. Estimating Natural Illumination from a Single Outdoor Image, poster in International Conference on Computational Photography, 2011. [PDF]|
Download the slides from the talk given at ICCV 2009 in the following formats:
- [MS Powerpoint, 27.3MB], export from Apple Keynote
- [PDF, 37.6MB]
- [Apple Keynote, 36.4MB], original version used at ICCV 2009.
You can download a subset of 391 webcam images that were used in the quantitative evaluation of the ICCV 2009 paper. You can also download the dataset of 239 single images that were used in the quantitative evaluation of the IJCV 2012 paper.
The entire code is now available!
This research is supported by:
- NSF CCF-0541230
- NSF IIS-0546547
- ONR N00014-08-1-0330
- NSF IIS-0643628
- Microsoft Research Fellowship
- Microsoft Research grant