Estimating Natural Illumination from a Single Outdoor Image - Robotics Institute Carnegie Mellon University

Estimating Natural Illumination from a Single Outdoor Image

Conference Paper, Proceedings of (ICCV) International Conference on Computer Vision, pp. 183 - 190, October, 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.

BibTeX

@conference{Lalonde-2009-10350,
author = {Jean-Francois Lalonde and Alexei A. Efros and Srinivasa G. Narasimhan},
title = {Estimating Natural Illumination from a Single Outdoor Image},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2009},
month = {October},
pages = {183 - 190},
}