Parallel volume rendering for 3D medical images

Abstract

Volume rendering is a technique for visualizing 3D arrays of sampled data. It has applications in areas such as medical imaging and scientific visualization, but its use has been limited by its computational expense and memory constraints. This thesis explores the use of parallel architectures for volume rendering. Parallel rendering is by no means a mature field, in fact efficient parallel rendering is an elusive goal. The problems encountered in parallel volume rendering algorithms include load imbalance, communication overheads and redundant computations. These problems are addressed in this thesis and new techniques are proposed to alleviate the compute inefficiency in parallel volume rendering algorithms.