Title:	SINGLE-IMAGE APPEARANCE ACQUISITION USING GENETIC ALGORITHMS
Author(s):	Adolfo Munoz , Belen Masia , Alfonso Tolosa , Diego Gutierrez
ISBN:	978-972-8924-84-3
Editors:	Yingcai Xiao, Tomaz Amon and Piet Kommers
Year:	2009
Edition:	Single
Keywords:	Appearance acquisition, inverse rendering, BSSRDF, reflectance, genetic algorithm.
Type:	Full Paper
First Page:	24
Last Page:	32
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	Most of the current appearance acquisition methods require the use of specialized equipment, involved capture sessions and/or large data sets. We propose a single-image approach which greatly simplifies the process, and allows to estimate reflectance properties of both opaque and translucent objects. Given the under-constrained nature of an image-based approach, we leverage two well-known illumination models, Phong and the diffuse approximation, to reduce the highdimensional parameter space. The formulation is that of an optimization problem and satisfactory results are obtained using an implementation based on genetic algorithms. Additionally, a study is carried out to provide guidance in the election of the configuration parameters of the genetic algorithm.
	Go Back