Logo image
Back
Reflectance and Natural Illumination from a Single Image
Conference proceeding   Open access   Peer reviewed

Reflectance and Natural Illumination from a Single Image

Stephen Lombardi and Ko Nishino
COMPUTER VISION - ECCV 2012, PT VI, v 7577(6), pp 582-595
01 Jan 2012
DOI: https://doi.org/10.1007/978-3-642-33783-3_42
url
https://doi.org/10.1007/978-3-642-33783-3_42View
Published, Version of Record (VoR)Maybe Open Access (Publisher Bronze),  Open

Abstract

Computer Science Computer Science, Artificial Intelligence Computer Science, Theory & Methods Imaging Science & Photographic Technology Science & Technology Technology
Estimating reflectance and natural illumination from a single image of an object of known shape is a challenging task due to the ambiguities between reflectance and illumination. Although there is an inherent limitation in what can be recovered as the reflectance band-limits the illumination, explicitly estimating both is desirable for many computer vision applications. Achieving this estimation requires that we derive and impose strong constraints on both variables. We introduce a probabilistic formulation that seamlessly incorporates such constraints as priors to arrive at the maximum a posteriori estimates of reflectance and natural illumination. We begin by showing that reflectance modulates the natural illumination in a way that increases its entropy. Based on this observation, we impose a prior on the illumination that favors lower entropy while conforming to natural image statistics. We also impose a prior on the reflectance based on the directional statistics BRDF model that constrains the estimate to lie within the bounds and variability of real-world materials. Experimental results on a number of synthetic and real images show that the method is able to achieve accurate joint estimation for different combinations of materials and lighting.

Metrics

9 Record Views
52 citations in Web of Science
48 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Computer Science, Artificial Intelligence
Computer Science, Theory & Methods
Imaging Science & Photographic Technology
Logo image