Parallel implementation of the stochastic radiosity method

Authors:
Roel Martínez;Jordi Coma
Affiliations:
Institut d'Informàtica i Aplicacions, Universitat de Girona;Escola Politècnica Superior, Universitat de Girona
Venue:
LSSC'09 Proceedings of the 7th international conference on Large-Scale Scientific Computing
Year:
2009

Citing 2
Cited 0

Illumination networks: fast realistic rendering with general reflectance functions

SIGGRAPH '89 Proceedings of the 16th annual conference on Computer graphics and interactive techniques
Efficient parallel global illumination using density estimation

PRS '95 Proceedings of the IEEE symposium on Parallel rendering

Quantified Score

Hi-index	0.00

Visualization

Abstract

To compute high quality images with a lot of polygons or patches may take hours For this reason parallel processing will be a good option in order to decrease the computational cost On the other hand, Monte Carlo methods offer good alternatives for parallelization, given their intrinsic decomposition properties in independent subtasks We have implemented the stochastic method for radiosity using a cluster of PCs Results are presented for 1 to 8 processors, exhibiting a good efficiency and scalability.