| | |
Summary: PROJECT REPORT
USING NEURAL NETWORKS FOR APPROXIMATE RADIOSITY FORM FACTOR
COMPUTATION
Submitted by
Charles Martin
Department of Computer Science
In partial ful llment of the requirements
for the degree of Master of Science
Colorado State University
Fort Collins, Colorado
Summer, 1996
ABSTRACT OF PROJECT REPORT
USING NEURAL NETWORKS FOR APPROXIMATE RADIOSITY FORM FACTOR
COMPUTATION
Radiosity is a method used in computer graphics to compute the distributionof di use
illumination within a scene. The largest cost of rendering a scene with radiosity is the
computation of geometrical relationships, called form factors, between each pair of objects
within the scene. This project report explores the use of neural networks to accelerate the
computation of radiosity form factors.
Charles Martin
|
