Parallel Volume Rendering Method for Out-of-Core Non-Uniformly Partitioned Datasets

摘要

The rapid development of graphics hardware has spawned a large number of GPU-based direct volume rendering methods. However, fast volume rendering for out-of-core datasets faces specific challenges, and many in-core-based methods cannot be applied to the volume rendering of out-of-core datasets. Although volume rendering algorithms based on partitioning strategies can effectively overcome these problems, the current partition-based techniques do not achieve a good balance between the partitioning method and the sub-block drawing method. In this paper, we propose an efficient out-of-core volume rendering method for datasets consisting of non-uniform size sub-blocks. The proposed method examines the parallel rendering possibilities between sub-blocks to accelerate the rendering process. Experimental comparisons with several volume rendering algorithms show that our method is faster than the current state-of-the-art approaches.