| | |
Summary: Statistics of Real-World Illumination
Ron O. Dror, Thomas K. Leung, Edward H. Adelson, and Alan S. Willsky
Artificial Intelligence Laboratory and Laboratory for Information and Decision Systems
Massachusetts Institute of Technology
rondror@ai.mit.edu, leungt@cs.berkeley.edu, adelson@psyche.mit.edu, willsky@mit.edu
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,
Kauai, Hawaii, December 2001. c IEEE Computer Society.
Abstract
While computer vision systems often assume simple illu-
mination models, real-world illumination is highly complex,
consisting of reflected light from every direction as well as
distributed and localized primary light sources. One can
capture the illumination incident at a point in the real world
from every direction photographically using a spherical il-
lumination map. This paper illustrates, through analysis
of photographically-acquired, high dynamic range illumi-
nation maps, that real-world illumination shares many of
the statistical properties of natural images. In particular,
the marginal and joint wavelet coefficient distributions, di-
rectional derivative distributions, and harmonic spectra of
|
