Performance of New GPU-Based Scan-Conversion Algorithm Implemented Using OpenGL

Abstract

A new GPU-based scan-conversion algorithm implemented using OpenGL is described. The compute performance of this new algorithm running on a modern GPU is compared to the performance of three common scan-conversion algorithms (nearest-neighbor, linear interpolation and bilinear interpolation) implemented in software using a modern CPU. The quality of the images produced by the algorithm, as measured by signal-to-noise power, is also compared to the quality of the images produced using these three common scan-conversion algorithms.