Implementation results and analysis of a parallel progressive radiosity

The quality of synthetic images depends, first, on the quality of the modelling of the three-dimensional scenes to visualize; more numerous are the geometrical and optical details, more realistic are the resulting images. Unfortunately, such scene descriptions need a big amount of memory, as well as a long time of computation. In order to deal with these restrictions, we propose a parallel implementation for an extended stochastic progressive radiosity method, where form factors are computed with a ray tracing scheme, on a network of processors with a distributed memory and a message passing mechanism. Our program has already treated very big scenes (more than one million patches for example).