GenTree: An Interactive Genetic Algorithms System for Designing 3D Polygonal Tree Models

Clare Bates Congdon¹ and Raymond H. Mazza²

¹Department of Computer Science
Colby College
5846 Mayflower Hill Drive
Waterville, ME 04901 USA
ccongdon@colby.edu

²Entertainment Technology Center
Carnegie Mellon University
5000 Forbes Avenue
Doherty Hall 4301
Pittsburgh, PA 15213 USA
rmazza@andrew.cmu.edu

Abstract. The creation of individual 3D models to include within a virtual world can be a time-consuming process. The standard approach to streamline this is to use procedural modeling tools, where the user adjusts a set of parameters that defines the tree. We have designed GenTree, an interactive system that uses a genetic algorithms (GA) approach to evolve procedural 3D tree models. GenTree is a hybrid system, combining the standard parameter adjustment and an interactive GA. The parameters may be changed by the user directly or via the GA process, which combines parameters from pairs of parent trees into those that describe novel trees. The GA component enables the system to be used by someone who is ignorant of the parameters that define the trees. Furthermore, combining the standard interactive design process with GA design decreases the time and patience required to design realistic 3D polygonal trees by either method alone.

LNCS 2724, p. 2034 ff.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003