Accelerated Filtering using OpenCL

Filtering is useful for noise reduction and edge detections in volumes. With the release of general purpose parallel computing interfaces, opportunities for increases in performance arises. In this paper I will present four volume filters, implemented using OpenCL. The filters consists of: a box filter, a Gaussian filter, a median filter and a central difference filter. The two first are implemented in a separable way, the latter ones are non-separable. Local memory on each streaming multiprocessor is used to speed up the memory access of the compute kernels. Comparison with CUDA implementation shows equivalent results, with the box filter showing better performance. Figure 1: To the left central difference filter and box filter applied on tooth data set. On the right same central difference filter followed by median filter. Rendering was done using Volumeshop [BG05].