Distributed ray casting for high-speed volume rendering. Master's thesis
The volume rendering technique known as ray casting or ray tracing is notoriously slow for large volume sizes, yet provides superior images. A technique is needed to accelerate ray tracing volumes without depending on special purpose or parallel computers. The realization and improvements in distributed computing over the past two decades has motivated its use in this work. This thesis explores a technique to speedup ray casting by distributed programming. The work investigates the possibility of dividing the volume among general purpose workstations and casting rays (using Levoy's front-to-back algorithm) through each subvolume independently. The final step being the composition of all subvolume rendered images. Results indicate a 75 percent savings in rendering time by distributed processing over eight processors versus a single processor.
- Research Organization:
- Air Force Inst. of Tech., Wright-Patterson AFB, OH (United States)
- OSTI ID:
- 5256645
- Report Number(s):
- AD-A-248167/9/XAB; AFIT/GCS/ENG-92M-01
- Resource Relation:
- Other Information: Thesis (M.S.)
- Country of Publication:
- United States
- Language:
- English
Similar Records
A data distributed, parallel algorithm for ray-traced volume rendering
Distributed processing in ray tracing