Breadth-first ray tracing utilizing uniform spatial subdivision

Breadth-first ray tracing is based on the idea of exchanging the roles of rays and objects. For scenes with a large number of objects, it may be profitable to form a set of rays and compare each object in turn against this set. By doing so, thrashing, due to disk access, can be minimized. In this paper, we present ways to combine breadth-first methods with traditional efficient algorithms, along with new schemes to minimize accessing objects stored on disk. Experimental analysis, including comparisons with depth-first ray tracing, shows that large databases can be handled efficiently with this approach.