Nonpolygonal Isosurface Rendering for Large Volume Datasets
Surface-based rendering techniques, particularly those that extract a polygonal approximation of an isosurface, are widely used in volume visualization. As dataset size increases though, the computational demands of these methods can overwhelm typically available computing resources. Recent work on accelerating such techniques has focused on preprocessing the volume data or postprocessing the extracted polygonization. Our new algorithm concentrates instead on streamlining the surface extraction process itself so as to accelerate the rendering of large volumes. The technique shortens the conventional isosurface visualization pipeline by eliminating the intermediate polygonization. We compute the contribution of the isosurface within a volume cell to the resulting image directly from a simplified numerical description of the cell/surface intersection. Our approach also reduces the work in the remaining stages of the visualization process. By quantizing the volume data, we exploit precomputed and cached data at key processing steps to improve rendering efficiency. The resulting implementation provides comparatively fast renderings with reasonable image quality.