Wei Hong, Feng Qiu, Arie Kaufman

1
Hybrid Volumetric Ray-Casting
Wei Hong, Feng Qiu, Arie Kaufman Center for
Visual Computing and Department of Computer
Science, Stony Brook University http//www.cs.suny
sb.edu/vislab/projects/gpgpu

• Overview
• Hybrid volumetric ray-casting algorithm using
  both CPU and GPU
• CPU ray traversal and empty space skipping
• GPU local illumination and ray integration
• Exploit the parallelism and trade-off between
  CPU and GPU to obtain further acceleration.

• Discussion
• Key innovations
• Exploit the parallelism of CPU and GPU
• Adjust the workload of CPU and GPU by controlling
• Number of steps processed in slab rendering
• Number of steps processed in fragment program

Figure 3 Two images inside the human colon.
(a)
(b)

• Results
• Platform
• 2.4 GHz Pentium 4 and 1G RAM
• Nvidia Geforce FX5950 with 256M RAM
• Average rendering (frames/sec)
• Rendering (frames/sec) for human colon
• Conclusion
• Our algorithm provides high quality and good
  performance for versatile direct volume rendering
  applications.

Figure 1 Overview of the algorithm
(a) Depth Image
(b) Intermediate Image
(c) Final Image

• Algorithm
• Ray Determination (CPU) Compute normalized ray
  direction and first intersection point - Figure
  1(a)
• Slab Rendering (GPU) Make each ray travel N
  steps forward - Figure 1(b)
• Hole Predicting (CPU) Find the non-terminated
  rays
• Hole Filling (GPU) Finish the non-terminated
  rays - Figure 1(c)

Figure 2 Volume rendering with different
transfer functions.
CT Engine
Visible Human Foot
Acknowledgement NSF CCR-03064