Speedup in Parallel Rendering System with Computational Best-effort Scheme

Virtual reality (VR) surgical training and presurgical planning require the creation of 3D virtual models of patient anatomy from medical scan data. Real-time head tracking in VR applications allows users to navigate in the virtual anatomy from any 3D position and orientation. The process of interactively rendering highly-detailed 3D volumetric data of anatomical models from a dynamically changing observer's perspective is extremely demanding for computational resources. Parallel computing presents a solution to this problem, involving a distributed volume graphics rendering system composed of multiple nodes concurrently working on different portions of the output streaming, which are later integrated to form the final view. This paper presents a distributed graphics rendering system consisting of multiple GPU-based heterogeneous nodes running a best-effort rendering scheme. Experiments show promising results in terms of efficiency and performance for rendering medical volumes in real time.