点光栅化及反走样算法的研究与实现

Design and Implementation of Point Scanning and Anti-aliasing

图形处理器流水线中经典的点生成算法和点反走样算法便于实现,但采样点测试的计算量大并且存在冗余测试,为此提出了多采样扫描转换算法。该算法将多采样集中在边界片元,同时,利用点区别于其他图元的对称特性,减少了采样点的冗余测试,提高了多采样时扫描转换的性能。试验结果表明:文中算法在较小代价下达到了同样的反走样性能。

The classical point-by-point generated algorithm and point anti-aliasing algorithm in graphic processing unit(GPU) pipeline are easy to realize,but the cost of sample testing is expensive and there is redundant testing. To slove this problem,this paper presented a multi-sampling scan conversion algorithm. The algorithm performed the sampling in side boundary fragment taking advantage of the symmetry properties of the point distinguished from other primitives. The redundant testing was reduced and the performance of scan conversion with multi-sampling was improved. The experimental results show that the algorithm achieves the performance of anti-aliasing at minimum cost.